Compare commits
2 Commits
feat/670-a
...
fix/712
| Author | SHA1 | Date | |
|---|---|---|---|
| c8bab8ae3c | |||
|
|
faaa08b3f1 |
@@ -1,68 +0,0 @@
|
||||
# Approval Tier System
|
||||
|
||||
Graduated safety based on risk level. Routes confirmations through the appropriate channel.
|
||||
|
||||
## Tiers
|
||||
|
||||
| Tier | Level | Actions | Human | LLM | Timeout |
|
||||
|------|-------|---------|-------|-----|---------|
|
||||
| 0 | SAFE | Read, search, browse | No | No | N/A |
|
||||
| 1 | LOW | Write, scripts, edits | No | Yes | N/A |
|
||||
| 2 | MEDIUM | Messages, API, shell exec | Yes | Yes | 60s |
|
||||
| 3 | HIGH | Destructive ops, config, deploys | Yes | Yes | 30s |
|
||||
| 4 | CRITICAL | Crisis, system destruction | Yes | Yes | 10s |
|
||||
|
||||
## How It Works
|
||||
|
||||
```
|
||||
Action submitted
|
||||
|
|
||||
v
|
||||
classify_tier() — pattern matching against TIER_PATTERNS
|
||||
|
|
||||
v
|
||||
ApprovalRouter.route() — based on tier:
|
||||
|
|
||||
+-- SAFE (0) → auto-approve
|
||||
+-- LOW (1) → smart-approve (LLM decides)
|
||||
+-- MEDIUM (2) → human confirmation, 60s timeout
|
||||
+-- HIGH (3) → human confirmation, 30s timeout
|
||||
+-- CRITICAL (4)→ crisis bypass OR human, 10s timeout
|
||||
```
|
||||
|
||||
## Crisis Bypass
|
||||
|
||||
Messages matching crisis patterns (suicidal ideation, method seeking) bypass normal approval entirely. They return crisis intervention resources:
|
||||
- 988 Suicide & Crisis Lifeline (call or text 988)
|
||||
- Crisis Text Line (text HOME to 741741)
|
||||
- Emergency: 911
|
||||
|
||||
## Timeout Handling
|
||||
|
||||
When a human confirmation times out:
|
||||
- MEDIUM (60s): Auto-escalate to HIGH
|
||||
- HIGH (30s): Auto-escalate to CRITICAL
|
||||
- CRITICAL (10s): Deny by default
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from tools.approval_tiers import classify_tier, ApprovalRouter
|
||||
|
||||
# Classify an action
|
||||
tier, reason = classify_tier("rm -rf /tmp/build")
|
||||
# tier == ApprovalTier.HIGH, reason == "recursive delete"
|
||||
|
||||
# Route for approval
|
||||
router = ApprovalRouter(session_key="my-session")
|
||||
result = router.route("rm -rf /tmp/build", description="Clean build artifacts")
|
||||
# result["approved"] == False, result["tier"] == "HIGH"
|
||||
|
||||
# Handle response
|
||||
if result["status"] == "approval_required":
|
||||
# Show confirmation UI, wait for user
|
||||
pass
|
||||
elif result["status"] == "crisis":
|
||||
# Show crisis resources
|
||||
pass
|
||||
```
|
||||
134
docs/cybersecurity-skills.md
Normal file
134
docs/cybersecurity-skills.md
Normal file
@@ -0,0 +1,134 @@
|
||||
# Anthropic Cybersecurity Skills Integration
|
||||
|
||||
Import and use the Anthropic Cybersecurity Skills library (754 skills, 26 domains, 5 frameworks) with Hermes Agent.
|
||||
|
||||
## Overview
|
||||
|
||||
The Anthropic Cybersecurity Skills library provides 754 production-grade security skills for AI agents. Each skill follows the agentskills.io standard with YAML frontmatter and structured decision-making workflows.
|
||||
|
||||
## Source
|
||||
|
||||
- **Repository:** https://github.com/mukul975/Anthropic-Cybersecurity-Skills
|
||||
- **License:** Apache 2.0
|
||||
- **Stars:** 4,385
|
||||
- **Compatible:** Hermes Agent, Claude Code, GitHub Copilot, Codex CLI
|
||||
|
||||
## Quick Start
|
||||
|
||||
```bash
|
||||
# Import all skills
|
||||
python scripts/import_cybersecurity_skills.py
|
||||
|
||||
# Import by domain
|
||||
python scripts/import_cybersecurity_skills.py --domain cloud-security
|
||||
|
||||
# Import by framework
|
||||
python scripts/import_cybersecurity_skills.py --framework nist-csf
|
||||
|
||||
# List available domains
|
||||
python scripts/import_cybersecurity_skills.py --list-domains
|
||||
|
||||
# List available frameworks
|
||||
python scripts/import_cybersecurity_skills.py --list-frameworks
|
||||
|
||||
# Dry run (show what would be imported)
|
||||
python scripts/import_cybersecurity_skills.py --dry-run
|
||||
```
|
||||
|
||||
## Security Domains (26)
|
||||
|
||||
| Domain | Skills | Key Capabilities |
|
||||
|--------|--------|-----------------|
|
||||
| Cloud Security | 60 | AWS, Azure, GCP hardening, CSPM, cloud forensics |
|
||||
| Threat Hunting | 55 | Hypothesis-driven hunts, LOTL detection, behavioral analytics |
|
||||
| Threat Intelligence | 50 | STIX/TAXII, MISP, feed integration, actor profiling |
|
||||
| Web App Security | 42 | OWASP Top 10, SQLi, XSS, SSRF, deserialization |
|
||||
| Network Security | 40 | IDS/IPS, firewall rules, VLAN segmentation |
|
||||
| Malware Analysis | 39 | Static/dynamic analysis, reverse engineering, sandboxing |
|
||||
| Digital Forensics | 37 | Disk imaging, memory forensics, timeline reconstruction |
|
||||
| Security Operations | 36 | SIEM correlation, log analysis, alert triage |
|
||||
| IAM | 35 | IAM policies, PAM, zero trust, Okta, SailPoint |
|
||||
| SOC Operations | 33 | Playbooks, escalation workflows, tabletop exercises |
|
||||
| Container Security | 30 | K8s RBAC, image scanning, Falco, container forensics |
|
||||
| OT/ICS Security | 28 | Modbus, DNP3, IEC 62443, SCADA |
|
||||
| API Security | 28 | GraphQL, REST, OWASP API Top 10, WAF bypass |
|
||||
| Vulnerability Management | 25 | Nessus, scanning workflows, CVSS |
|
||||
| Incident Response | 25 | Breach containment, ransomware response, IR playbooks |
|
||||
| Red Teaming | 24 | Full-scope engagements, AD attacks, phishing simulation |
|
||||
| Penetration Testing | 23 | Network, web, cloud, mobile, wireless |
|
||||
| Endpoint Security | 17 | EDR, LOTL detection, fileless malware |
|
||||
| DevSecOps | 17 | CI/CD security, code signing, Terraform auditing |
|
||||
| Phishing Defense | 16 | Email auth, BEC detection, phishing IR |
|
||||
| Cryptography | 14 | Key management, TLS, certificate analysis |
|
||||
|
||||
## Framework Mappings (5)
|
||||
|
||||
| Framework | Version | Scope |
|
||||
|-----------|---------|-------|
|
||||
| MITRE ATT&CK | v18 | 14 tactics, 200+ techniques |
|
||||
| NIST CSF 2.0 | 2.0 | 6 functions, 22 categories |
|
||||
| MITRE ATLAS | v5.4 | 16 tactics, 84 techniques |
|
||||
| MITRE D3FEND | v1.3 | 7 categories, 267 techniques |
|
||||
| NIST AI RMF | 1.0 | 4 functions, 72 subcategories |
|
||||
|
||||
## Skill Format
|
||||
|
||||
Each skill follows the agentskills.io standard:
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: analyzing-active-directory-acl-abuse
|
||||
description: Detect dangerous ACL misconfigurations in Active Directory
|
||||
domain: cybersecurity
|
||||
subdomain: identity-security
|
||||
tags:
|
||||
- active-directory
|
||||
- acl-abuse
|
||||
- ldap
|
||||
version: '1.0'
|
||||
author: mahipal
|
||||
license: Apache-2.0
|
||||
nist_csf:
|
||||
- PR.AA-01
|
||||
- PR.AA-05
|
||||
- PR.AA-06
|
||||
---
|
||||
```
|
||||
|
||||
## Use Cases for Hermes
|
||||
|
||||
1. **Fleet security** — Agents can audit their own infrastructure
|
||||
2. **Incident response** — Structured IR playbooks for security events
|
||||
3. **Threat hunting** — Hypothesis-driven hunts across fleet logs
|
||||
4. **Compliance** — Framework-mapped skills for audit preparation
|
||||
5. **Training** — Security skills for agents to learn and apply
|
||||
|
||||
## Integration with Hermes Skills
|
||||
|
||||
The imported skills are compatible with Hermes Agent's skill system:
|
||||
|
||||
```bash
|
||||
# Skills are installed to ~/.hermes/skills/cybersecurity/
|
||||
# Each skill has a SKILL.md file with YAML frontmatter
|
||||
|
||||
# Use in Hermes
|
||||
hermes skills list | grep cybersecurity
|
||||
hermes skills enable cybersecurity/cloud-security
|
||||
```
|
||||
|
||||
## Adding to Fleet
|
||||
|
||||
```bash
|
||||
# Import all skills
|
||||
python scripts/import_cybersecurity_skills.py
|
||||
|
||||
# Import specific domain for fleet security
|
||||
python scripts/import_cybersecurity_skills.py --domain incident-response
|
||||
|
||||
# Import for compliance
|
||||
python scripts/import_cybersecurity_skills.py --framework nist-csf
|
||||
```
|
||||
|
||||
## Index
|
||||
|
||||
After import, an index is generated at `~/.hermes/skills/cybersecurity/index.json` listing all installed skills with their metadata.
|
||||
227
scripts/import-cybersecurity-skills.py
Normal file
227
scripts/import-cybersecurity-skills.py
Normal file
@@ -0,0 +1,227 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
import-cybersecurity-skills.py — Import Anthropic Cybersecurity Skills into Hermes.
|
||||
|
||||
Clones the Anthropic-Cybersecurity-Skills repo and creates a skill index
|
||||
that maps each of the 754 skills to the Hermes optional-skills format.
|
||||
|
||||
Usage:
|
||||
python3 scripts/import-cybersecurity-skills.py --clone # Clone repo
|
||||
python3 scripts/import-cybersecurity-skills.py --index # Generate skill index
|
||||
python3 scripts/import-cybersecurity-skills.py --install DOMAIN # Install skills for a domain
|
||||
python3 scripts/import-cybersecurity-skills.py --list # List all domains
|
||||
python3 scripts/import-cybersecurity-skills.py --status # Import status
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import yaml
|
||||
from pathlib import Path
|
||||
from collections import defaultdict
|
||||
|
||||
REPO_URL = "https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git"
|
||||
SKILLS_DIR = Path.home() / ".hermes" / "cybersecurity-skills"
|
||||
INDEX_PATH = SKILLS_DIR / "skill-index.json"
|
||||
OPTIONAL_SKILLS_DIR = Path.home() / ".hermes" / "optional-skills" / "cybersecurity"
|
||||
|
||||
# Domain → hermes category mapping
|
||||
DOMAIN_CATEGORIES = {
|
||||
"cloud-security": "security",
|
||||
"threat-hunting": "security",
|
||||
"threat-intelligence": "security",
|
||||
"web-app-security": "security",
|
||||
"network-security": "security",
|
||||
"malware-analysis": "security",
|
||||
"digital-forensics": "security",
|
||||
"security-operations": "security",
|
||||
"identity-access-management": "security",
|
||||
"soc-operations": "security",
|
||||
"container-security": "security",
|
||||
"ot-ics-security": "security",
|
||||
"api-security": "security",
|
||||
"vulnerability-management": "security",
|
||||
"incident-response": "security",
|
||||
"red-teaming": "security",
|
||||
"penetration-testing": "security",
|
||||
"endpoint-security": "security",
|
||||
"devsecops": "devops",
|
||||
"phishing-defense": "security",
|
||||
"cryptography": "security",
|
||||
}
|
||||
|
||||
|
||||
def cmd_clone():
|
||||
"""Clone the cybersecurity skills repository."""
|
||||
if SKILLS_DIR.exists():
|
||||
print(f"Updating existing clone at {SKILLS_DIR}")
|
||||
subprocess.run(["git", "-C", str(SKILLS_DIR), "pull"], capture_output=True)
|
||||
else:
|
||||
SKILLS_DIR.parent.mkdir(parents=True, exist_ok=True)
|
||||
print(f"Cloning {REPO_URL} to {SKILLS_DIR}")
|
||||
subprocess.run(["git", "clone", "--depth", "1", REPO_URL, str(SKILLS_DIR)], capture_output=True)
|
||||
|
||||
# Count skills
|
||||
skill_files = list(SKILLS_DIR.rglob("*.md"))
|
||||
print(f"Found {len(skill_files)} skill files")
|
||||
|
||||
|
||||
def cmd_index():
|
||||
"""Generate a skill index from the cloned repo."""
|
||||
if not SKILLS_DIR.exists():
|
||||
print("Run --clone first", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
skills = []
|
||||
domains = defaultdict(list)
|
||||
|
||||
for md_file in SKILLS_DIR.rglob("*.md"):
|
||||
if md_file.name in ("README.md", "LICENSE.md", "DESCRIPTION.md"):
|
||||
continue
|
||||
|
||||
try:
|
||||
content = md_file.read_text(errors="ignore")
|
||||
except OSError:
|
||||
continue
|
||||
|
||||
# Parse YAML frontmatter
|
||||
if content.startswith("---"):
|
||||
parts = content.split("---", 2)
|
||||
if len(parts) >= 3:
|
||||
try:
|
||||
frontmatter = yaml.safe_load(parts[1]) or {}
|
||||
except yaml.YAMLError:
|
||||
frontmatter = {}
|
||||
else:
|
||||
frontmatter = {}
|
||||
else:
|
||||
frontmatter = {}
|
||||
|
||||
# Extract metadata
|
||||
name = frontmatter.get("name", md_file.stem)
|
||||
description = frontmatter.get("description", "")
|
||||
domain = frontmatter.get("domain", frontmatter.get("subdomain", "general"))
|
||||
tags = frontmatter.get("tags", [])
|
||||
frameworks = frontmatter.get("nist_csf", []) + frontmatter.get("mitre_attack", [])
|
||||
|
||||
skill = {
|
||||
"name": name,
|
||||
"file": str(md_file.relative_to(SKILLS_DIR)),
|
||||
"description": description[:200],
|
||||
"domain": domain,
|
||||
"tags": tags[:5],
|
||||
"frameworks": frameworks[:5] if isinstance(frameworks, list) else [],
|
||||
"size_kb": round(md_file.stat().st_size / 1024, 1),
|
||||
}
|
||||
skills.append(skill)
|
||||
domains[domain].append(name)
|
||||
|
||||
# Build index
|
||||
index = {
|
||||
"total_skills": len(skills),
|
||||
"total_domains": len(domains),
|
||||
"domains": {k: len(v) for k, v in sorted(domains.items())},
|
||||
"skills": sorted(skills, key=lambda s: s["domain"]),
|
||||
"generated_from": REPO_URL,
|
||||
}
|
||||
|
||||
INDEX_PATH.write_text(json.dumps(index, indent=2))
|
||||
print(f"Indexed {len(skills)} skills across {len(domains)} domains")
|
||||
print(f"Written to {INDEX_PATH}")
|
||||
|
||||
# Print domain summary
|
||||
print("\nDomains:")
|
||||
for domain, count in sorted(domains.items(), key=lambda x: -len(x[1])):
|
||||
print(f" {domain}: {count} skills")
|
||||
|
||||
|
||||
def cmd_list():
|
||||
"""List all security domains."""
|
||||
if not INDEX_PATH.exists():
|
||||
print("Run --index first", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
index = json.loads(INDEX_PATH.read_text())
|
||||
print(f"Total: {index['total_skills']} skills across {index['total_domains']} domains\n")
|
||||
for domain, count in sorted(index["domains"].items(), key=lambda x: -x[1]):
|
||||
print(f" {domain:<35} {count:>4} skills")
|
||||
|
||||
|
||||
def cmd_install(domain: str = None):
|
||||
"""Install skills for a domain into optional-skills."""
|
||||
if not INDEX_PATH.exists():
|
||||
print("Run --index first", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
index = json.loads(INDEX_PATH.read_text())
|
||||
skills = index["skills"]
|
||||
|
||||
if domain:
|
||||
skills = [s for s in skills if s["domain"] == domain]
|
||||
if not skills:
|
||||
print(f"No skills found for domain: {domain}")
|
||||
sys.exit(1)
|
||||
|
||||
installed = 0
|
||||
for skill in skills:
|
||||
# Create skill directory
|
||||
category = DOMAIN_CATEGORIES.get(skill["domain"], "security")
|
||||
skill_dir = OPTIONAL_SKILLS_DIR / category / skill["name"]
|
||||
skill_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Copy source file
|
||||
src = SKILLS_DIR / skill["file"]
|
||||
if src.exists():
|
||||
dst = skill_dir / "SKILL.md"
|
||||
dst.write_text(src.read_text(errors="ignore"))
|
||||
installed += 1
|
||||
|
||||
print(f"Installed {installed} skills to {OPTIONAL_SKILLS_DIR}")
|
||||
|
||||
|
||||
def cmd_status():
|
||||
"""Show import status."""
|
||||
print(f"Clone dir: {SKILLS_DIR}")
|
||||
print(f" Exists: {SKILLS_DIR.exists()}")
|
||||
|
||||
print(f"Index: {INDEX_PATH}")
|
||||
print(f" Exists: {INDEX_PATH.exists()}")
|
||||
if INDEX_PATH.exists():
|
||||
index = json.loads(INDEX_PATH.read_text())
|
||||
print(f" Skills: {index['total_skills']}")
|
||||
print(f" Domains: {index['total_domains']}")
|
||||
|
||||
print(f"Install dir: {OPTIONAL_SKILLS_DIR}")
|
||||
print(f" Exists: {OPTIONAL_SKILLS_DIR.exists()}")
|
||||
if OPTIONAL_SKILLS_DIR.exists():
|
||||
installed = len(list(OPTIONAL_SKILLS_DIR.rglob("SKILL.md")))
|
||||
print(f" Installed skills: {installed}")
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Import Anthropic Cybersecurity Skills")
|
||||
parser.add_argument("--clone", action="store_true", help="Clone the skills repo")
|
||||
parser.add_argument("--index", action="store_true", help="Generate skill index")
|
||||
parser.add_argument("--list", action="store_true", help="List all domains")
|
||||
parser.add_argument("--install", metavar="DOMAIN", nargs="?", const="all", help="Install skills for domain")
|
||||
parser.add_argument("--status", action="store_true", help="Import status")
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.clone:
|
||||
cmd_clone()
|
||||
elif args.index:
|
||||
cmd_index()
|
||||
elif args.list:
|
||||
cmd_list()
|
||||
elif args.install is not None:
|
||||
cmd_install(None if args.install == "all" else args.install)
|
||||
elif args.status:
|
||||
cmd_status()
|
||||
else:
|
||||
parser.print_help()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
245
scripts/import_cybersecurity_skills.py
Normal file
245
scripts/import_cybersecurity_skills.py
Normal file
@@ -0,0 +1,245 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
import_cybersecurity_skills.py — Import Anthropic Cybersecurity Skills Library
|
||||
|
||||
Downloads and integrates the Anthropic Cybersecurity Skills library into
|
||||
Hermes Agent's skill system.
|
||||
|
||||
Source: https://github.com/mukul975/Anthropic-Cybersecurity-Skills
|
||||
License: Apache 2.0
|
||||
Skills: 754 across 26 security domains, 5 frameworks
|
||||
|
||||
Usage:
|
||||
python scripts/import_cybersecurity_skills.py
|
||||
python scripts/import_cybersecurity_skills.py --domain cloud-security
|
||||
python scripts/import_cybersecurity_skills.py --framework nist-csf
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import shutil
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
from typing import List, Dict, Any
|
||||
|
||||
# Configuration
|
||||
REPO_URL = "https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git"
|
||||
SKILLS_DIR = Path.home() / ".hermes" / "skills" / "cybersecurity"
|
||||
CACHE_DIR = Path.home() / ".hermes" / "cache" / "cybersecurity-skills"
|
||||
|
||||
# Framework mappings
|
||||
FRAMEWORKS = {
|
||||
"mitre-attack": "MITRE ATT&CK v18",
|
||||
"nist-csf": "NIST CSF 2.0",
|
||||
"mitre-atlas": "MITRE ATLAS v5.4",
|
||||
"mitre-d3fend": "MITRE D3FEND v1.3",
|
||||
"nist-ai-rmf": "NIST AI RMF 1.0",
|
||||
}
|
||||
|
||||
# Security domains
|
||||
DOMAINS = [
|
||||
"cloud-security", "threat-hunting", "threat-intelligence",
|
||||
"web-app-security", "network-security", "malware-analysis",
|
||||
"digital-forensics", "security-operations", "iam",
|
||||
"soc-operations", "container-security", "ot-ics-security",
|
||||
"api-security", "vulnerability-management", "incident-response",
|
||||
"red-teaming", "penetration-testing", "endpoint-security",
|
||||
"devsecops", "phishing-defense", "cryptography",
|
||||
]
|
||||
|
||||
|
||||
def clone_repo(target_dir: Path) -> bool:
|
||||
"""Clone the cybersecurity skills repository."""
|
||||
print(f"Cloning {REPO_URL}...")
|
||||
try:
|
||||
subprocess.run(
|
||||
["git", "clone", "--depth", "1", REPO_URL, str(target_dir)],
|
||||
check=True,
|
||||
capture_output=True,
|
||||
)
|
||||
return True
|
||||
except subprocess.CalledProcessError as e:
|
||||
print(f"Error cloning repository: {e}", file=sys.stderr)
|
||||
return False
|
||||
|
||||
|
||||
def parse_skill_file(skill_path: Path) -> Dict[str, Any]:
|
||||
"""Parse a skill YAML/Markdown file."""
|
||||
content = skill_path.read_text(encoding="utf-8")
|
||||
|
||||
# Extract YAML frontmatter
|
||||
if content.startswith("---"):
|
||||
parts = content.split("---", 2)
|
||||
if len(parts) >= 3:
|
||||
import yaml
|
||||
try:
|
||||
metadata = yaml.safe_load(parts[1])
|
||||
metadata["content"] = parts[2].strip()
|
||||
metadata["path"] = str(skill_path)
|
||||
return metadata
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Fallback: use filename as name
|
||||
return {
|
||||
"name": skill_path.stem,
|
||||
"description": content[:200],
|
||||
"content": content,
|
||||
"path": str(skill_path),
|
||||
}
|
||||
|
||||
|
||||
def find_skills(repo_dir: Path, domain: str = None, framework: str = None) -> List[Path]:
|
||||
"""Find skill files in the repository."""
|
||||
skills = []
|
||||
|
||||
# Look for skills in common locations
|
||||
search_dirs = [
|
||||
repo_dir / "skills",
|
||||
repo_dir / "cybersecurity",
|
||||
repo_dir,
|
||||
]
|
||||
|
||||
for search_dir in search_dirs:
|
||||
if not search_dir.exists():
|
||||
continue
|
||||
|
||||
for path in search_dir.rglob("*.md"):
|
||||
# Skip README files
|
||||
if path.name.upper() == "README.MD":
|
||||
continue
|
||||
|
||||
# Filter by domain if specified
|
||||
if domain:
|
||||
if domain.lower() not in str(path).lower():
|
||||
continue
|
||||
|
||||
# Filter by framework if specified
|
||||
if framework:
|
||||
content = path.read_text(encoding="utf-8", errors="ignore").lower()
|
||||
if framework.lower() not in content:
|
||||
continue
|
||||
|
||||
skills.append(path)
|
||||
|
||||
return skills
|
||||
|
||||
|
||||
def install_skills(skills: List[Path], target_dir: Path) -> int:
|
||||
"""Install skills to Hermes skill directory."""
|
||||
target_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
installed = 0
|
||||
for skill_path in skills:
|
||||
skill = parse_skill_file(skill_path)
|
||||
name = skill.get("name", skill_path.stem)
|
||||
|
||||
# Create skill directory
|
||||
skill_dir = target_dir / name
|
||||
skill_dir.mkdir(exist_ok=True)
|
||||
|
||||
# Copy skill file
|
||||
dest = skill_dir / "SKILL.md"
|
||||
shutil.copy2(skill_path, dest)
|
||||
|
||||
installed += 1
|
||||
|
||||
return installed
|
||||
|
||||
|
||||
def generate_index(skills_dir: Path) -> Dict[str, Any]:
|
||||
"""Generate an index of installed skills."""
|
||||
index = {
|
||||
"source": "Anthropic Cybersecurity Skills Library",
|
||||
"url": REPO_URL,
|
||||
"license": "Apache-2.0",
|
||||
"skills": [],
|
||||
}
|
||||
|
||||
for skill_dir in skills_dir.iterdir():
|
||||
if not skill_dir.is_dir():
|
||||
continue
|
||||
|
||||
skill_file = skill_dir / "SKILL.md"
|
||||
if not skill_file.exists():
|
||||
continue
|
||||
|
||||
skill = parse_skill_file(skill_file)
|
||||
index["skills"].append({
|
||||
"name": skill.get("name", skill_dir.name),
|
||||
"description": skill.get("description", "")[:200],
|
||||
"domain": skill.get("domain", ""),
|
||||
"frameworks": skill.get("frameworks", []),
|
||||
})
|
||||
|
||||
return index
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Import Anthropic Cybersecurity Skills")
|
||||
parser.add_argument("--domain", "-d", help="Filter by security domain")
|
||||
parser.add_argument("--framework", "-f", help="Filter by framework (e.g., nist-csf)")
|
||||
parser.add_argument("--list-domains", action="store_true", help="List available domains")
|
||||
parser.add_argument("--list-frameworks", action="store_true", help="List available frameworks")
|
||||
parser.add_argument("--output", "-o", help="Output directory for skills")
|
||||
parser.add_argument("--dry-run", action="store_true", help="Show what would be imported")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# List domains
|
||||
if args.list_domains:
|
||||
print("Available security domains:")
|
||||
for domain in DOMAINS:
|
||||
print(f" - {domain}")
|
||||
return
|
||||
|
||||
# List frameworks
|
||||
if args.list_frameworks:
|
||||
print("Available frameworks:")
|
||||
for key, name in FRAMEWORKS.items():
|
||||
print(f" - {key}: {name}")
|
||||
return
|
||||
|
||||
# Set output directory
|
||||
output_dir = Path(args.output) if args.output else SKILLS_DIR
|
||||
|
||||
# Clone repository
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
repo_dir = Path(tmpdir) / "cybersecurity-skills"
|
||||
|
||||
if not clone_repo(repo_dir):
|
||||
sys.exit(1)
|
||||
|
||||
# Find skills
|
||||
print(f"Searching for skills (domain={args.domain}, framework={args.framework})...")
|
||||
skills = find_skills(repo_dir, args.domain, args.framework)
|
||||
print(f"Found {len(skills)} skills")
|
||||
|
||||
if args.dry_run:
|
||||
print("\nDry run — skills that would be imported:")
|
||||
for skill_path in skills[:20]:
|
||||
skill = parse_skill_file(skill_path)
|
||||
print(f" - {skill.get('name', skill_path.stem)}: {skill.get('description', '')[:60]}...")
|
||||
if len(skills) > 20:
|
||||
print(f" ... and {len(skills) - 20} more")
|
||||
return
|
||||
|
||||
# Install skills
|
||||
print(f"Installing to {output_dir}...")
|
||||
installed = install_skills(skills, output_dir)
|
||||
print(f"Installed {installed} skills")
|
||||
|
||||
# Generate index
|
||||
index = generate_index(output_dir)
|
||||
index_path = output_dir / "index.json"
|
||||
with open(index_path, "w") as f:
|
||||
json.dump(index, f, indent=2)
|
||||
print(f"Index saved to {index_path}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,223 +0,0 @@
|
||||
"""Tests for the Approval Tier System — issue #670."""
|
||||
|
||||
import pytest
|
||||
from tools.approval_tiers import (
|
||||
ApprovalTier,
|
||||
classify_tier,
|
||||
is_crisis,
|
||||
ApprovalRouter,
|
||||
route_action,
|
||||
)
|
||||
|
||||
|
||||
class TestApprovalTierEnum:
|
||||
def test_tier_values(self):
|
||||
assert ApprovalTier.SAFE == 0
|
||||
assert ApprovalTier.LOW == 1
|
||||
assert ApprovalTier.MEDIUM == 2
|
||||
assert ApprovalTier.HIGH == 3
|
||||
assert ApprovalTier.CRITICAL == 4
|
||||
|
||||
def test_tier_labels(self):
|
||||
assert ApprovalTier.SAFE.label == "SAFE"
|
||||
assert ApprovalTier.CRITICAL.label == "CRITICAL"
|
||||
|
||||
def test_timeout_seconds(self):
|
||||
assert ApprovalTier.SAFE.timeout_seconds is None
|
||||
assert ApprovalTier.LOW.timeout_seconds is None
|
||||
assert ApprovalTier.MEDIUM.timeout_seconds == 60
|
||||
assert ApprovalTier.HIGH.timeout_seconds == 30
|
||||
assert ApprovalTier.CRITICAL.timeout_seconds == 10
|
||||
|
||||
def test_requires_human(self):
|
||||
assert not ApprovalTier.SAFE.requires_human
|
||||
assert not ApprovalTier.LOW.requires_human
|
||||
assert ApprovalTier.MEDIUM.requires_human
|
||||
assert ApprovalTier.HIGH.requires_human
|
||||
assert ApprovalTier.CRITICAL.requires_human
|
||||
|
||||
|
||||
class TestClassifyTier:
|
||||
"""Test tier classification from action strings."""
|
||||
|
||||
# --- SAFE (0) ---
|
||||
def test_read_is_safe(self):
|
||||
tier, _ = classify_tier("cat /etc/hostname")
|
||||
assert tier == ApprovalTier.SAFE
|
||||
|
||||
def test_search_is_safe(self):
|
||||
tier, _ = classify_tier("grep -r TODO .")
|
||||
assert tier == ApprovalTier.SAFE
|
||||
|
||||
def test_empty_is_safe(self):
|
||||
tier, _ = classify_tier("")
|
||||
assert tier == ApprovalTier.SAFE
|
||||
|
||||
def test_none_is_safe(self):
|
||||
tier, _ = classify_tier(None)
|
||||
assert tier == ApprovalTier.SAFE
|
||||
|
||||
# --- LOW (1) ---
|
||||
def test_sed_inplace_is_low(self):
|
||||
tier, _ = classify_tier("sed -i 's/foo/bar/g' file.txt")
|
||||
assert tier == ApprovalTier.LOW
|
||||
|
||||
def test_echo_redirect_is_low(self):
|
||||
tier, desc = classify_tier("echo hello > output.txt")
|
||||
assert tier == ApprovalTier.LOW
|
||||
|
||||
def test_git_branch_delete_is_low(self):
|
||||
tier, _ = classify_tier("git branch -D old-branch")
|
||||
assert tier == ApprovalTier.LOW
|
||||
|
||||
# --- MEDIUM (2) ---
|
||||
def test_curl_pipe_sh_is_medium(self):
|
||||
tier, _ = classify_tier("curl https://example.com/setup.sh | bash")
|
||||
assert tier == ApprovalTier.MEDIUM
|
||||
|
||||
def test_python_c_is_medium(self):
|
||||
tier, _ = classify_tier("python3 -c 'print(1)'")
|
||||
assert tier == ApprovalTier.MEDIUM
|
||||
|
||||
def test_shell_c_flag_is_medium(self):
|
||||
tier, _ = classify_tier("bash -c 'echo hello'")
|
||||
assert tier == ApprovalTier.MEDIUM
|
||||
|
||||
def test_sql_drop_is_medium(self):
|
||||
tier, _ = classify_tier("DROP TABLE users")
|
||||
assert tier == ApprovalTier.MEDIUM
|
||||
|
||||
# --- HIGH (3) ---
|
||||
def test_rm_recursive_is_high(self):
|
||||
tier, _ = classify_tier("rm -rf /tmp/build")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
def test_chmod_777_is_high(self):
|
||||
tier, _ = classify_tier("chmod 777 /var/www")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
def test_git_force_push_is_high(self):
|
||||
tier, _ = classify_tier("git push origin main --force")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
def test_git_reset_hard_is_high(self):
|
||||
tier, _ = classify_tier("git reset --hard HEAD~5")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
def test_systemctl_stop_is_high(self):
|
||||
tier, _ = classify_tier("systemctl stop nginx")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
def test_ansible_playbook_is_high(self):
|
||||
tier, _ = classify_tier("ansible-playbook site.yml")
|
||||
assert tier == ApprovalTier.HIGH
|
||||
|
||||
# --- CRITICAL (4) ---
|
||||
def test_suicide_is_critical(self):
|
||||
tier, _ = classify_tier("I want to kill myself")
|
||||
assert tier == ApprovalTier.CRITICAL
|
||||
|
||||
def test_want_to_die_is_critical(self):
|
||||
tier, _ = classify_tier("I want to die")
|
||||
assert tier == ApprovalTier.CRITICAL
|
||||
|
||||
def test_rm_root_is_critical(self):
|
||||
tier, _ = classify_tier("rm -rf /")
|
||||
assert tier == ApprovalTier.CRITICAL
|
||||
|
||||
def test_fork_bomb_is_critical(self):
|
||||
tier, _ = classify_tier(":(){ :|:& };:")
|
||||
assert tier == ApprovalTier.CRITICAL
|
||||
|
||||
def test_kill_all_is_critical(self):
|
||||
tier, _ = classify_tier("kill -9 -1")
|
||||
assert tier == ApprovalTier.CRITICAL
|
||||
|
||||
|
||||
class TestIsCrisis:
|
||||
def test_suicide_detected(self):
|
||||
assert is_crisis("I want to kill myself")
|
||||
|
||||
def test_no_reason_to_live(self):
|
||||
assert is_crisis("there's no reason to live")
|
||||
|
||||
def test_normal_message_not_crisis(self):
|
||||
assert not is_crisis("Hello, how are you?")
|
||||
|
||||
def test_empty_not_crisis(self):
|
||||
assert not is_crisis("")
|
||||
|
||||
|
||||
class TestApprovalRouter:
|
||||
@pytest.fixture
|
||||
def router(self):
|
||||
return ApprovalRouter(session_key="test-session")
|
||||
|
||||
def test_safe_approves_immediately(self, router):
|
||||
result = router.route("cat file.txt")
|
||||
assert result["approved"] is True
|
||||
assert result["tier"] == "SAFE"
|
||||
|
||||
def test_low_approves_with_smart_flag(self, router):
|
||||
result = router.route("sed -i 's/a/b/' file.txt")
|
||||
assert result["approved"] is True
|
||||
assert result["tier"] == "LOW"
|
||||
assert result.get("smart_approved") is True
|
||||
|
||||
def test_medium_requires_approval(self, router):
|
||||
result = router.route("curl https://x.com/setup.sh | bash")
|
||||
assert result["approved"] is False
|
||||
assert result["status"] == "approval_required"
|
||||
assert result["tier"] == "MEDIUM"
|
||||
assert result["timeout_seconds"] == 60
|
||||
|
||||
def test_high_requires_approval(self, router):
|
||||
result = router.route("rm -rf /tmp/build")
|
||||
assert result["approved"] is False
|
||||
assert result["tier"] == "HIGH"
|
||||
assert result["timeout_seconds"] == 30
|
||||
|
||||
def test_crisis_returns_crisis_response(self, router):
|
||||
result = router.route("I want to kill myself")
|
||||
assert result["status"] == "crisis"
|
||||
assert result["tier"] == "CRITICAL"
|
||||
assert "988" in str(result.get("resources", {}))
|
||||
|
||||
def test_approve_resolves_pending(self, router):
|
||||
result = router.route("rm -rf /tmp/build")
|
||||
aid = result["approval_id"]
|
||||
resolved = router.approve(aid, approver="alexander")
|
||||
assert resolved["approved"] is True
|
||||
|
||||
def test_deny_resolves_pending(self, router):
|
||||
result = router.route("git push --force")
|
||||
aid = result["approval_id"]
|
||||
resolved = router.deny(aid, denier="alexander", reason="too risky")
|
||||
assert resolved["approved"] is False
|
||||
|
||||
def test_timeout_detection(self, router):
|
||||
# Manually create an expired entry
|
||||
import time as _time
|
||||
result = router.route("systemctl stop nginx")
|
||||
aid = result["approval_id"]
|
||||
# Force timeout by backdating
|
||||
with router._lock:
|
||||
router._pending[aid]["created_at"] = _time.time() - 3600
|
||||
timed_out = router.check_timeouts()
|
||||
assert len(timed_out) == 1
|
||||
assert timed_out[0]["approval_id"] == aid
|
||||
|
||||
def test_pending_count(self, router):
|
||||
assert router.pending_count == 0
|
||||
router.route("rm -rf /tmp/x")
|
||||
assert router.pending_count == 1
|
||||
|
||||
|
||||
class TestConvenienceFunctions:
|
||||
def test_route_action(self):
|
||||
result = route_action("cat file.txt")
|
||||
assert result["approved"] is True
|
||||
|
||||
def test_classify_tier_with_context(self):
|
||||
tier, _ = classify_tier("echo hi", context={"platform": "telegram"})
|
||||
assert tier == ApprovalTier.SAFE
|
||||
@@ -6,7 +6,6 @@ This module is the single source of truth for the dangerous command system:
|
||||
- Approval prompting (CLI interactive + gateway async)
|
||||
- Smart approval via auxiliary LLM (auto-approve low-risk commands)
|
||||
- Permanent allowlist persistence (config.yaml)
|
||||
- 5-tier approval system with graduated safety (Issue #670)
|
||||
"""
|
||||
|
||||
import contextvars
|
||||
@@ -15,190 +14,11 @@ import os
|
||||
import re
|
||||
import sys
|
||||
import threading
|
||||
import time
|
||||
import unicodedata
|
||||
from enum import Enum
|
||||
from typing import Optional, Tuple, Dict, Any
|
||||
from typing import Optional
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# =========================================================================
|
||||
# Approval Tier System (Issue #670)
|
||||
# =========================================================================
|
||||
#
|
||||
# 5 tiers of graduated safety. Each tier defines what approval is required
|
||||
# and how long the user has to respond before auto-escalation.
|
||||
#
|
||||
# Tier 0 (SAFE): Read, search, list. No approval needed.
|
||||
# Tier 1 (LOW): Write, scripts, edits. LLM approval sufficient.
|
||||
# Tier 2 (MEDIUM): Messages, API calls, external actions. Human + LLM.
|
||||
# Tier 3 (HIGH): Crypto, config changes, deployment. Human + LLM, 30s timeout.
|
||||
# Tier 4 (CRITICAL): Crisis, self-modification, system destruction. Human + LLM, 10s timeout.
|
||||
# =========================================================================
|
||||
|
||||
class ApprovalTier(Enum):
|
||||
"""Five approval tiers from SAFE (no approval) to CRITICAL (human + fast timeout)."""
|
||||
SAFE = 0
|
||||
LOW = 1
|
||||
MEDIUM = 2
|
||||
HIGH = 3
|
||||
CRITICAL = 4
|
||||
|
||||
|
||||
# Tier configuration: human_required, llm_required, timeout_seconds
|
||||
TIER_CONFIG: Dict[ApprovalTier, Dict[str, Any]] = {
|
||||
ApprovalTier.SAFE: {"human_required": False, "llm_required": False, "timeout_sec": None},
|
||||
ApprovalTier.LOW: {"human_required": False, "llm_required": True, "timeout_sec": None},
|
||||
ApprovalTier.MEDIUM: {"human_required": True, "llm_required": True, "timeout_sec": 60},
|
||||
ApprovalTier.HIGH: {"human_required": True, "llm_required": True, "timeout_sec": 30},
|
||||
ApprovalTier.CRITICAL: {"human_required": True, "llm_required": True, "timeout_sec": 10},
|
||||
}
|
||||
|
||||
# Action types mapped to tiers
|
||||
ACTION_TIER_MAP: Dict[str, ApprovalTier] = {
|
||||
# Tier 0: Safe read operations
|
||||
"read": ApprovalTier.SAFE,
|
||||
"search": ApprovalTier.SAFE,
|
||||
"list": ApprovalTier.SAFE,
|
||||
"query": ApprovalTier.SAFE,
|
||||
"check": ApprovalTier.SAFE,
|
||||
"status": ApprovalTier.SAFE,
|
||||
"log": ApprovalTier.SAFE,
|
||||
"diff": ApprovalTier.SAFE,
|
||||
|
||||
# Tier 1: Low-risk writes
|
||||
"write": ApprovalTier.LOW,
|
||||
"edit": ApprovalTier.LOW,
|
||||
"patch": ApprovalTier.LOW,
|
||||
"create": ApprovalTier.LOW,
|
||||
"delete": ApprovalTier.LOW,
|
||||
"move": ApprovalTier.LOW,
|
||||
"copy": ApprovalTier.LOW,
|
||||
"mkdir": ApprovalTier.LOW,
|
||||
"script": ApprovalTier.LOW,
|
||||
"test": ApprovalTier.LOW,
|
||||
"lint": ApprovalTier.LOW,
|
||||
"format": ApprovalTier.LOW,
|
||||
|
||||
# Tier 2: External actions
|
||||
"message": ApprovalTier.MEDIUM,
|
||||
"send": ApprovalTier.MEDIUM,
|
||||
"api_call": ApprovalTier.MEDIUM,
|
||||
"webhook": ApprovalTier.MEDIUM,
|
||||
"email": ApprovalTier.MEDIUM,
|
||||
"notify": ApprovalTier.MEDIUM,
|
||||
"commit": ApprovalTier.MEDIUM,
|
||||
"push": ApprovalTier.MEDIUM,
|
||||
"branch": ApprovalTier.MEDIUM,
|
||||
"pr": ApprovalTier.MEDIUM,
|
||||
"deploy": ApprovalTier.MEDIUM,
|
||||
"install": ApprovalTier.MEDIUM,
|
||||
|
||||
# Tier 3: High-risk operations
|
||||
"config": ApprovalTier.HIGH,
|
||||
"crypto": ApprovalTier.HIGH,
|
||||
"key": ApprovalTier.HIGH,
|
||||
"secret": ApprovalTier.HIGH,
|
||||
"credential": ApprovalTier.HIGH,
|
||||
"auth": ApprovalTier.HIGH,
|
||||
"permission": ApprovalTier.HIGH,
|
||||
"firewall": ApprovalTier.HIGH,
|
||||
"network": ApprovalTier.HIGH,
|
||||
"database": ApprovalTier.HIGH,
|
||||
"migration": ApprovalTier.HIGH,
|
||||
"systemd": ApprovalTier.HIGH,
|
||||
|
||||
# Tier 4: Critical / crisis
|
||||
"crisis": ApprovalTier.CRITICAL,
|
||||
"suicide": ApprovalTier.CRITICAL,
|
||||
"kill": ApprovalTier.CRITICAL,
|
||||
"destroy": ApprovalTier.CRITICAL,
|
||||
"format": ApprovalTier.CRITICAL,
|
||||
"wipe": ApprovalTier.CRITICAL,
|
||||
"nuke": ApprovalTier.CRITICAL,
|
||||
"self_modify": ApprovalTier.CRITICAL,
|
||||
}
|
||||
|
||||
# Crisis bypass: these patterns auto-resolve to crisis response, no approval
|
||||
CRISIS_BYPASS_PATTERNS = [
|
||||
(r'\b(?:kill|end)\s+(?:myself|my\s+life)\b', "suicidal ideation"),
|
||||
(r'\bwant\s+to\s+die\b', "suicidal ideation"),
|
||||
(r'\bwant\s+to\s+end\s+(?:it|everything|my\s+life)\b', "suicidal ideation"),
|
||||
(r'\bno\s+reason\s+to\s+live\b', "hopelessness"),
|
||||
(r'\bbetter\s+off\s+dead\b', "hopelessness"),
|
||||
(r'\bwish\s+I\s+(?:was|were)\s+dead\b', "hopelessness"),
|
||||
]
|
||||
|
||||
|
||||
def classify_action_tier(action: str, command: str = "") -> ApprovalTier:
|
||||
"""Determine the approval tier for an action.
|
||||
|
||||
Args:
|
||||
action: The action type (e.g., "write", "deploy", "crisis")
|
||||
command: The full command text for pattern matching
|
||||
|
||||
Returns:
|
||||
The highest applicable ApprovalTier
|
||||
"""
|
||||
tier = ApprovalTier.SAFE
|
||||
|
||||
# Check for crisis bypass first (always highest priority)
|
||||
if command:
|
||||
for pattern, _ in CRISIS_BYPASS_PATTERNS:
|
||||
if re.search(pattern, command, re.IGNORECASE):
|
||||
return ApprovalTier.CRITICAL
|
||||
|
||||
# Check action type mapping
|
||||
action_lower = action.lower().strip()
|
||||
if action_lower in ACTION_TIER_MAP:
|
||||
tier = ACTION_TIER_MAP[action_lower]
|
||||
|
||||
# Always check dangerous patterns in command — can upgrade tier
|
||||
if command:
|
||||
is_dangerous, _, _ = detect_dangerous_command(command)
|
||||
if is_dangerous and tier.value < ApprovalTier.HIGH.value:
|
||||
tier = ApprovalTier.HIGH
|
||||
|
||||
return tier
|
||||
|
||||
|
||||
def requires_approval(tier: ApprovalTier) -> bool:
|
||||
"""Check if a tier requires any form of approval (human or LLM)."""
|
||||
config = TIER_CONFIG[tier]
|
||||
return config["human_required"] or config["llm_required"]
|
||||
|
||||
|
||||
def requires_human(tier: ApprovalTier) -> bool:
|
||||
"""Check if a tier requires human approval."""
|
||||
return TIER_CONFIG[tier]["human_required"]
|
||||
|
||||
|
||||
def requires_llm(tier: ApprovalTier) -> bool:
|
||||
"""Check if a tier requires LLM approval."""
|
||||
return TIER_CONFIG[tier]["llm_required"]
|
||||
|
||||
|
||||
def get_timeout(tier: ApprovalTier) -> Optional[int]:
|
||||
"""Get the approval timeout in seconds for a tier. None = no timeout."""
|
||||
return TIER_CONFIG[tier]["timeout_sec"]
|
||||
|
||||
|
||||
def classify_and_check(action: str, command: str = "") -> Tuple[ApprovalTier, bool, Optional[int]]:
|
||||
"""Classify an action and return its approval requirements.
|
||||
|
||||
Args:
|
||||
action: The action type
|
||||
command: The full command text
|
||||
|
||||
Returns:
|
||||
Tuple of (tier, needs_approval, timeout_seconds)
|
||||
"""
|
||||
tier = classify_action_tier(action, command)
|
||||
needs = requires_approval(tier)
|
||||
timeout = get_timeout(tier)
|
||||
return tier, needs, timeout
|
||||
|
||||
# Per-thread/per-task gateway session identity.
|
||||
# Gateway runs agent turns concurrently in executor threads, so reading a
|
||||
# process-global env var for session identity is racy. Keep env fallback for
|
||||
|
||||
@@ -1,386 +0,0 @@
|
||||
"""Approval Tier System — graduated safety based on risk level.
|
||||
|
||||
Extends the existing approval.py dangerous-command detection with a 5-tier
|
||||
system that routes confirmations through the appropriate channel based on
|
||||
risk severity.
|
||||
|
||||
Tiers:
|
||||
SAFE (0) — Read, search, browse. No confirmation needed.
|
||||
LOW (1) — Write, scripts, edits. LLM smart approval sufficient.
|
||||
MEDIUM (2) — Messages, API calls. Human + LLM, 60s timeout.
|
||||
HIGH (3) — Crypto, config changes, deploys. Human + LLM, 30s timeout.
|
||||
CRITICAL (4) — Crisis, self-harm, system destruction. Immediate human, 10s timeout.
|
||||
|
||||
Usage:
|
||||
from tools.approval_tiers import classify_tier, ApprovalTier
|
||||
tier = classify_tier("rm -rf /")
|
||||
# tier == ApprovalTier.CRITICAL
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import threading
|
||||
import time
|
||||
from enum import IntEnum
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ApprovalTier(IntEnum):
|
||||
"""Graduated safety tiers for action approval.
|
||||
|
||||
Lower numbers = less dangerous. Higher = more dangerous.
|
||||
Each tier has different confirmation requirements.
|
||||
"""
|
||||
SAFE = 0
|
||||
LOW = 1
|
||||
MEDIUM = 2
|
||||
HIGH = 3
|
||||
CRITICAL = 4
|
||||
|
||||
@property
|
||||
def label(self) -> str:
|
||||
return {
|
||||
0: "SAFE",
|
||||
1: "LOW",
|
||||
2: "MEDIUM",
|
||||
3: "HIGH",
|
||||
4: "CRITICAL",
|
||||
}[self.value]
|
||||
|
||||
@property
|
||||
def emoji(self) -> str:
|
||||
return {
|
||||
0: "\u2705", # check mark
|
||||
1: "\U0001f7e1", # yellow circle
|
||||
2: "\U0001f7e0", # orange circle
|
||||
3: "\U0001f534", # red circle
|
||||
4: "\U0001f6a8", # warning
|
||||
}[self.value]
|
||||
|
||||
@property
|
||||
def timeout_seconds(self) -> Optional[int]:
|
||||
"""Timeout before auto-escalation. None = no timeout."""
|
||||
return {
|
||||
0: None, # no confirmation needed
|
||||
1: None, # LLM decides, no timeout
|
||||
2: 60, # 60s for medium risk
|
||||
3: 30, # 30s for high risk
|
||||
4: 10, # 10s for critical
|
||||
}[self.value]
|
||||
|
||||
@property
|
||||
def requires_human(self) -> bool:
|
||||
"""Whether this tier requires human confirmation."""
|
||||
return self.value >= 2
|
||||
|
||||
@property
|
||||
def requires_llm(self) -> bool:
|
||||
"""Whether this tier benefits from LLM smart approval."""
|
||||
return self.value >= 1
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tier classification patterns
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Each entry: (regex_pattern, tier, description)
|
||||
# Patterns are checked in order; first match wins.
|
||||
|
||||
TIER_PATTERNS: List[Tuple[str, int, str]] = [
|
||||
# === TIER 4: CRITICAL — Immediate danger ===
|
||||
# Crisis / self-harm
|
||||
(r'\b(?:kill|end)\s+(?:myself|my\s+life)\b', 4, "crisis: suicidal ideation"),
|
||||
(r'\bwant\s+to\s+die\b', 4, "crisis: suicidal ideation"),
|
||||
(r'\bsuicidal\b', 4, "crisis: suicidal ideation"),
|
||||
(r'\bhow\s+(?:do\s+I|to|can\s+I)\s+(?:kill|hang|overdose|cut)\s+myself\b', 4, "crisis: method seeking"),
|
||||
|
||||
# System destruction
|
||||
(r'\brm\s+(-[^\s]*\s+)*/$', 4, "delete in root path"),
|
||||
(r'\brm\s+-rf\s+[~/]', 4, "recursive force delete of home"),
|
||||
(r'\bmkfs\b', 4, "format filesystem"),
|
||||
(r'\bdd\s+.*of=/dev/', 4, "write to block device"),
|
||||
(r'\bkill\s+-9\s+-1\b', 4, "kill all processes"),
|
||||
(r'\b:\(\)\s*\{\s*:\s*\|\s*:\s*&\s*\}\s*;\s*:', 4, "fork bomb"),
|
||||
|
||||
# === TIER 3: HIGH — Destructive or sensitive ===
|
||||
(r'\brm\s+-[^ ]*r\b', 3, "recursive delete"),
|
||||
(r'\bchmod\s+(777|666|o\+[rwx]*w|a\+[rwx]*w)\b', 3, "world-writable permissions"),
|
||||
(r'\bchown\s+.*root', 3, "chown to root"),
|
||||
(r'>\s*/etc/', 3, "overwrite system config"),
|
||||
(r'\bgit\s+push\b.*--force\b', 3, "git force push"),
|
||||
(r'\bgit\s+reset\s+--hard\b', 3, "git reset --hard"),
|
||||
(r'\bsystemctl\s+(stop|disable|mask)\b', 3, "stop/disable system service"),
|
||||
|
||||
# Deployment and config
|
||||
(r'\b(?:deploy|publish|release)\b.*(?:prod|production)\b', 3, "production deploy"),
|
||||
(r'\bansible-playbook\b', 3, "run Ansible playbook"),
|
||||
(r'\bdocker\s+(?:rm|stop|kill)\b.*(?:-f|--force)\b', 3, "force stop/remove container"),
|
||||
|
||||
# === TIER 2: MEDIUM — External actions ===
|
||||
(r'\bcurl\b.*\|\s*(ba)?sh\b', 2, "pipe remote content to shell"),
|
||||
(r'\bwget\b.*\|\s*(ba)?sh\b', 2, "pipe remote content to shell"),
|
||||
(r'\b(bash|sh|zsh)\s+-[^ ]*c\b', 2, "shell command via -c flag"),
|
||||
(r'\b(python|perl|ruby|node)\s+-[ec]\s+', 2, "script execution via flag"),
|
||||
(r'\b(python|perl|ruby|node)\s+<<', 2, "script execution via heredoc"),
|
||||
(r'\bDROP\s+(TABLE|DATABASE)\b', 2, "SQL DROP"),
|
||||
(r'\bDELETE\s+FROM\b(?!.*\bWHERE\b)', 2, "SQL DELETE without WHERE"),
|
||||
|
||||
# Messaging / external APIs
|
||||
(r'\bsend_message\b.*(?:telegram|discord|slack)\b', 2, "send message to platform"),
|
||||
(r'\bhttp[s]?://\b.*\bPOST\b', 2, "HTTP POST request"),
|
||||
|
||||
# === TIER 1: LOW — File modifications ===
|
||||
(r'\btee\b.*>', 1, "write file via tee"),
|
||||
(r'\becho\b.*>\s*(?!/dev/null)', 1, "write file via echo redirect"),
|
||||
(r'\bsed\s+-[^ ]*i\b', 1, "in-place file edit"),
|
||||
(r'\bcp\b.*\s/etc/', 1, "copy file into /etc/"),
|
||||
(r'\bmv\b.*\s/etc/', 1, "move file into /etc/"),
|
||||
(r'\bgit\s+branch\s+-D\b', 1, "git branch force delete"),
|
||||
(r'\bgit\s+clean\s+-[^ ]*f\b', 1, "git clean force"),
|
||||
|
||||
# === TIER 0: SAFE (explicit, for completeness) ===
|
||||
# Read-only operations don't match any pattern above,
|
||||
# so they default to SAFE.
|
||||
]
|
||||
|
||||
|
||||
# Crisis bypass: if a message matches a crisis pattern, route
|
||||
# directly to crisis intervention (skip normal approval flow).
|
||||
CRISIS_BYPASS_PATTERNS = [
|
||||
r'\b(?:kill|end)\s+(?:myself|my\s+life)\b',
|
||||
r'\bwant\s+to\s+die\b',
|
||||
r'\bsuicidal\b',
|
||||
r'\bno\s+reason\s+to\s+live\b',
|
||||
r'\bbetter\s+off\s+dead\b',
|
||||
r'\bwish\s+I\s+(?:was|were)\s+dead\b',
|
||||
r'\bhow\s+(?:do\s+I|to)\s+(?:kill|hang|overdose)\s+myself\b',
|
||||
r'\bmethods?\s+of\s+(?:suicide|dying)\b',
|
||||
]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tier classification
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def classify_tier(action: str, context: Optional[Dict[str, Any]] = None) -> Tuple[ApprovalTier, str]:
|
||||
"""Classify an action into an approval tier.
|
||||
|
||||
Args:
|
||||
action: The command, message, or action to classify.
|
||||
context: Optional context (platform, session_key, etc.)
|
||||
|
||||
Returns:
|
||||
(tier, description) tuple. Tier is an ApprovalTier enum,
|
||||
description explains why this tier was chosen.
|
||||
"""
|
||||
if not action or not isinstance(action, str):
|
||||
return (ApprovalTier.SAFE, "empty or non-string input")
|
||||
|
||||
# Check crisis bypass first (always CRITICAL)
|
||||
for pattern in CRISIS_BYPASS_PATTERNS:
|
||||
if re.search(pattern, action, re.IGNORECASE):
|
||||
return (ApprovalTier.CRITICAL, f"crisis detected: {pattern[:30]}")
|
||||
|
||||
# Check tier patterns (highest tier first, patterns are ordered)
|
||||
for pattern, tier_value, description in TIER_PATTERNS:
|
||||
if re.search(pattern, action, re.IGNORECASE | re.DOTALL):
|
||||
return (ApprovalTier(tier_value), description)
|
||||
|
||||
# Default: SAFE
|
||||
return (ApprovalTier.SAFE, "no dangerous patterns detected")
|
||||
|
||||
|
||||
def is_crisis(action: str) -> bool:
|
||||
"""Check if an action/message indicates a crisis situation.
|
||||
|
||||
If True, the action should bypass normal approval and go directly
|
||||
to crisis intervention.
|
||||
"""
|
||||
if not action:
|
||||
return False
|
||||
for pattern in CRISIS_BYPASS_PATTERNS:
|
||||
if re.search(pattern, action, re.IGNORECASE):
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Tier-based approval routing
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
class ApprovalRouter:
|
||||
"""Routes approval requests through the appropriate channel based on tier.
|
||||
|
||||
Handles:
|
||||
- Telegram inline keyboard confirmations
|
||||
- Discord reaction confirmations
|
||||
- CLI prompt confirmations
|
||||
- Timeout-based auto-escalation
|
||||
- Crisis bypass
|
||||
"""
|
||||
|
||||
def __init__(self, session_key: str = "default"):
|
||||
self._session_key = session_key
|
||||
self._pending: Dict[str, Dict[str, Any]] = {}
|
||||
self._lock = threading.Lock()
|
||||
|
||||
def route(self, action: str, description: str = "",
|
||||
context: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
|
||||
"""Route an action for approval based on its tier.
|
||||
|
||||
Returns a result dict:
|
||||
- {"approved": True} for SAFE tier or auto-approved
|
||||
- {"approved": False, "status": "pending", ...} for human approval
|
||||
- {"approved": False, "status": "crisis", ...} for crisis bypass
|
||||
"""
|
||||
tier, reason = classify_tier(action, context)
|
||||
|
||||
# Crisis bypass: skip normal approval, return crisis response
|
||||
if tier == ApprovalTier.CRITICAL and is_crisis(action):
|
||||
return {
|
||||
"approved": False,
|
||||
"status": "crisis",
|
||||
"tier": tier.label,
|
||||
"reason": reason,
|
||||
"action_required": "crisis_intervention",
|
||||
"resources": {
|
||||
"lifeline": "988 Suicide & Crisis Lifeline (call or text 988)",
|
||||
"crisis_text": "Crisis Text Line (text HOME to 741741)",
|
||||
"emergency": "911",
|
||||
},
|
||||
}
|
||||
|
||||
# SAFE tier: no confirmation needed
|
||||
if tier == ApprovalTier.SAFE:
|
||||
return {
|
||||
"approved": True,
|
||||
"tier": tier.label,
|
||||
"reason": reason,
|
||||
}
|
||||
|
||||
# LOW tier: LLM smart approval (if available), otherwise approve
|
||||
if tier == ApprovalTier.LOW:
|
||||
return {
|
||||
"approved": True,
|
||||
"tier": tier.label,
|
||||
"reason": reason,
|
||||
"smart_approved": True,
|
||||
}
|
||||
|
||||
# MEDIUM, HIGH, CRITICAL: require human confirmation
|
||||
approval_id = f"{self._session_key}:{int(time.time() * 1000)}"
|
||||
|
||||
with self._lock:
|
||||
self._pending[approval_id] = {
|
||||
"action": action,
|
||||
"description": description,
|
||||
"tier": tier,
|
||||
"reason": reason,
|
||||
"created_at": time.time(),
|
||||
"timeout": tier.timeout_seconds,
|
||||
}
|
||||
|
||||
return {
|
||||
"approved": False,
|
||||
"status": "approval_required",
|
||||
"approval_id": approval_id,
|
||||
"tier": tier.label,
|
||||
"tier_emoji": tier.emoji,
|
||||
"reason": reason,
|
||||
"timeout_seconds": tier.timeout_seconds,
|
||||
"message": (
|
||||
f"{tier.emoji} **{tier.label}** action requires confirmation.\n"
|
||||
f"**Action:** {action[:200]}\n"
|
||||
f"**Reason:** {reason}\n"
|
||||
f"**Timeout:** {tier.timeout_seconds}s (auto-escalate on timeout)"
|
||||
),
|
||||
}
|
||||
|
||||
def approve(self, approval_id: str, approver: str = "user") -> Dict[str, Any]:
|
||||
"""Mark a pending approval as approved."""
|
||||
with self._lock:
|
||||
entry = self._pending.pop(approval_id, None)
|
||||
if entry is None:
|
||||
return {"error": f"Approval {approval_id} not found"}
|
||||
return {
|
||||
"approved": True,
|
||||
"tier": entry["tier"].label,
|
||||
"approver": approver,
|
||||
"action": entry["action"],
|
||||
}
|
||||
|
||||
def deny(self, approval_id: str, denier: str = "user",
|
||||
reason: str = "") -> Dict[str, Any]:
|
||||
"""Mark a pending approval as denied."""
|
||||
with self._lock:
|
||||
entry = self._pending.pop(approval_id, None)
|
||||
if entry is None:
|
||||
return {"error": f"Approval {approval_id} not found"}
|
||||
return {
|
||||
"approved": False,
|
||||
"tier": entry["tier"].label,
|
||||
"denier": denier,
|
||||
"action": entry["action"],
|
||||
"reason": reason,
|
||||
}
|
||||
|
||||
def check_timeouts(self) -> List[Dict[str, Any]]:
|
||||
"""Check and return any approvals that have timed out.
|
||||
|
||||
Called periodically by the gateway. Returns list of timed-out
|
||||
entries that should be auto-escalated (denied or escalated
|
||||
to a higher channel).
|
||||
"""
|
||||
now = time.time()
|
||||
timed_out = []
|
||||
with self._lock:
|
||||
for aid, entry in list(self._pending.items()):
|
||||
timeout = entry.get("timeout")
|
||||
if timeout is None:
|
||||
continue
|
||||
elapsed = now - entry["created_at"]
|
||||
if elapsed > timeout:
|
||||
self._pending.pop(aid, None)
|
||||
timed_out.append({
|
||||
"approval_id": aid,
|
||||
"action": entry["action"],
|
||||
"tier": entry["tier"].label,
|
||||
"elapsed": elapsed,
|
||||
"timeout": timeout,
|
||||
})
|
||||
return timed_out
|
||||
|
||||
@property
|
||||
def pending_count(self) -> int:
|
||||
with self._lock:
|
||||
return len(self._pending)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Convenience functions
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Module-level router instance
|
||||
_default_router: Optional[ApprovalRouter] = None
|
||||
_router_lock = threading.Lock()
|
||||
|
||||
|
||||
def get_router(session_key: str = "default") -> ApprovalRouter:
|
||||
"""Get or create the approval router for a session."""
|
||||
global _default_router
|
||||
with _router_lock:
|
||||
if _default_router is None or _default_router._session_key != session_key:
|
||||
_default_router = ApprovalRouter(session_key)
|
||||
return _default_router
|
||||
|
||||
|
||||
def route_action(action: str, description: str = "",
|
||||
context: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
|
||||
"""Convenience: classify and route an action for approval."""
|
||||
router = get_router(context.get("session_key", "default") if context else "default")
|
||||
return router.route(action, description, context)
|
||||
Reference in New Issue
Block a user