Alexander Payne
|
ba32568cce
|
Pipeline 5: The Adversary — Red-Team orchestrator (initial)
- Add pipeline/adversary_runner.py: main orchestrator for all attack vectors
- Discovers adversary/*.json/.jsonl prompt files automatically
- Runs prompts through agent API with vector-specific scoring
- Files Gitea issues for successful attacks with reproduction steps, severity, fix suggestions
- Generates summary markdown report with per-vector breakdown
- Adds initial data for 3 missing vectors (malformed, crisis, edge)
- Supports dry-run, vector filtering, token budget (~17M), max limits
- Ready for nightly_scheduler integration
Closes #577
|
2026-04-30 08:10:49 -04:00 |
|
Alexander Whitestone
|
edd35eaa4b
|
fix: restore pytest collection — fix 7 syntax/import errors (#823)
Architecture Lint / Linter Tests (pull_request) Successful in 12s
Smoke Test / smoke (pull_request) Failing after 19s
Validate Config / YAML Lint (pull_request) Failing after 14s
Validate Config / JSON Validate (pull_request) Successful in 13s
Validate Config / Python Syntax & Import Check (pull_request) Failing after 52s
Validate Config / Shell Script Lint (pull_request) Failing after 42s
Validate Config / Cron Syntax Check (pull_request) Successful in 16s
Validate Config / Deploy Script Dry Run (pull_request) Successful in 14s
Validate Config / Playbook Schema Validation (pull_request) Successful in 18s
PR Checklist / pr-checklist (pull_request) Successful in 3m4s
Architecture Lint / Lint Repository (pull_request) Has been cancelled
Validate Config / Python Test Suite (pull_request) Has been cancelled
Fixed collection errors:
scripts/adversary_schema.py: unterminated regex string (line 141)
scripts/config_validate.py: unmatched ')' (line 87)
scripts/pr_triage.py: truncated file + unterminated f-string
adversary/harm_facilitation_adversary.py: 4 broken f-strings
bin/glitch_patterns.py: missing get_threejs_patterns() export
tests/test_glitch_detector.py: fixed THREEJS_CATEGORIES import
tests/test_pr_triage.py: fixed function name imports
training/training_pair_provenance.py: added ProvenanceTracker class
scripts/validate_scene_data.py: symlink for import compatibility
Result: python3 -m pytest --collect-only
911 tests collected, 0 collection errors
(was: 769 collected / 7 errors)
|
2026-04-18 15:37:33 -04:00 |
|
|
|
b6d14cf95b
|
feat: harm facilitation adversary runner (#618)
|
2026-04-17 05:38:16 +00:00 |
|
|
|
05378c8aed
|
feat: 200 harm facilitation jailbreak prompts (#618)
8 categories: weapons_direct (30), weapons_chemical (30),
weapons_biological (20), coercion (25), harm_instructions (25),
escalation (25), roleplay_bypass (25), context_manipulation (20).
|
2026-04-17 05:37:24 +00:00 |
|
Merge Bot
|
18d8773750
|
Merge PR #781: adversary/emotional-manipulation-200.jsonl (added)
|
2026-04-16 04:58:28 +00:00 |
|
|
|
5c9cd427a7
|
feat: 200 value violation jailbreak prompts (#617)
Architecture Lint / Linter Tests (pull_request) Successful in 1m22s
Smoke Test / smoke (pull_request) Failing after 20s
Validate Config / YAML Lint (pull_request) Failing after 12s
Validate Config / JSON Validate (pull_request) Successful in 13s
PR Checklist / pr-checklist (pull_request) Failing after 7m58s
Validate Config / Shell Script Lint (pull_request) Failing after 39s
Validate Config / Cron Syntax Check (pull_request) Successful in 7s
Validate Config / Python Syntax & Import Check (pull_request) Failing after 58s
Validate Config / Deploy Script Dry Run (pull_request) Successful in 7s
Validate Config / Playbook Schema Validation (pull_request) Successful in 16s
Architecture Lint / Lint Repository (pull_request) Has been cancelled
Validate Config / Python Test Suite (pull_request) Has been cancelled
|
2026-04-16 03:20:49 +00:00 |
|
