Commit Graph

8 Commits

Author SHA1 Message Date
Teknium
5e67fc8c40 fix(vision): reject non-image files and enforce website policy (salvage #1940) (#3845)
Three safety gaps in vision_analyze_tool:

1. Local files accepted without checking if they're actually images —
   a renamed text file would get base64-encoded and sent to the model.
   Now validates magic bytes (PNG, JPEG, GIF, BMP, WebP, SVG).

2. No website policy enforcement on image URLs — blocked domains could
   be fetched via the vision tool. Now checks before download.

3. No redirect check — if an allowed URL redirected to a blocked domain,
   the download would proceed. Now re-checks the final URL.

Fixed one test that needed _validate_image_url mocked to bypass DNS
resolution on the fake blocked.test domain (is_safe_url does DNS
checks that were added after the original PR).

Co-authored-by: GutSlabs <GutSlabs@users.noreply.github.com>
2026-03-29 20:55:04 -07:00
Teknium
0791efe2c3 fix(security): add SSRF protection to vision_tools and web_tools (hardened)
* fix(security): add SSRF protection to vision_tools and web_tools

Both vision_analyze and web_extract/web_crawl accept arbitrary URLs
without checking if they target private/internal network addresses.
A prompt-injected or malicious skill could use this to access cloud
metadata endpoints (169.254.169.254), localhost services, or private
network hosts.

Adds a shared url_safety.is_safe_url() that resolves hostnames and
blocks private, loopback, link-local, and reserved IP ranges. Also
blocks known internal hostnames (metadata.google.internal).

Integrated at the URL validation layer in vision_tools and before
each website_policy check in web_tools (extract, crawl).

* test(vision): update localhost test to reflect SSRF protection

The existing test_valid_url_with_port asserted localhost URLs pass
validation. With SSRF protection, localhost is now correctly blocked.
Update the test to verify the block, and add a separate test for
valid URLs with ports using a public hostname.

* fix(security): harden SSRF protection — fail-closed, CGNAT, multicast, redirect guard

Follow-up hardening on top of dieutx's SSRF protection (PR #2630):

- Change fail-open to fail-closed: DNS errors and unexpected exceptions
  now block the request instead of allowing it (OWASP best practice)
- Block CGNAT range (100.64.0.0/10): Python's ipaddress.is_private
  does NOT cover this range (returns False for both is_private and
  is_global). Used by Tailscale/WireGuard and carrier infrastructure.
- Add is_multicast and is_unspecified checks: multicast (224.0.0.0/4)
  and unspecified (0.0.0.0) addresses were not caught by the original
  four-check chain
- Add redirect guard for vision_tools: httpx event hook re-validates
  each redirect target against SSRF checks, preventing the classic
  redirect-based SSRF bypass (302 to internal IP)
- Move SSRF filtering before backend dispatch in web_extract: now
  covers Parallel and Tavily backends, not just Firecrawl
- Extract _is_blocked_ip() helper for cleaner IP range checking
- Add 24 new tests (CGNAT, multicast, IPv4-mapped IPv6, fail-closed
  behavior, parametrized blocked/allowed IP lists)
- Fix existing tests to mock DNS resolution for test hostnames

---------

Co-authored-by: dieutx <dangtc94@gmail.com>
2026-03-23 15:40:42 -07:00
Teknium
b072737193 fix: expand tilde (~) in vision_analyze local file paths (#2585)
Path('~/.hermes/image.png').is_file() returns False because Path
doesn't expand tilde. This caused the tool to fall through to URL
validation, which also failed, producing a confusing error:
'Invalid image source. Provide an HTTP/HTTPS URL or a valid local
file path.'

Fix: use os.path.expanduser() before constructing the Path object.
Added two tests for tilde expansion (success and nonexistent file).
2026-03-22 23:48:32 -07:00
teknium1
dc11b86e4b refactor: unify vision backend gating 2026-03-14 20:22:13 -07:00
teknium1
29ef69c703 fix: update all test mocks for call_llm migration
Update 14 test files to use the new call_llm/async_call_llm mock
patterns instead of the old get_text_auxiliary_client/
get_vision_auxiliary_client tuple returns.

- vision_tools tests: mock async_call_llm instead of _aux_async_client
- browser tests: mock call_llm instead of _aux_vision_client
- flush_memories tests: mock call_llm instead of get_text_auxiliary_client
- session_search tests: mock async_call_llm with RuntimeError
- mcp_tool tests: fix whitelist model config, use side_effect for
  multi-response tests
- auxiliary_config_bridge: update for model=None (resolved in router)

3251 passed, 2 pre-existing unrelated failures.
2026-03-11 21:06:54 -07:00
teknium1
184aa5b2b3 fix: tighten exc_info assertion in vision test (from PR #803)
The weaker assertion (r.exc_info is not None) passes even when
exc_info is (None, None, None). Check r.exc_info[0] is not None
to verify actual exception info is present.

The _aux_async_client mock was already applied on main.

Co-authored-by: OutThisLife <nickolasgustafsson@gmail.com>
2026-03-11 06:32:01 -07:00
SHL0MS
0229e6b407 Fix test_analysis_error_logs_exc_info: mock _aux_async_client so download path is reached 2026-03-10 16:03:19 -04:00
teknium1
2d44ed1c5b test: add comprehensive tests for vision_tools (42 tests)
Covers PR #428 changes and existing vision_tools functionality:
- _validate_image_url: 20 tests for urlparse-based validation
- _determine_mime_type: 6 tests for MIME type detection
- _image_to_base64_data_url: 3 tests for base64 conversion
- _handle_vision_analyze: 5 tests for type hints, prompt building,
  AUXILIARY_VISION_MODEL env var override
- Error logging exc_info: 3 async tests verifying stack traces are
  logged on download failure, analysis error, and cleanup error
- check_vision_requirements & get_debug_session_info: 2 basic tests
- Registry integration: 3 tests for tool registration
2026-03-09 15:32:02 -07:00