76aa97f77b
Close three variant bypasses adjacent to VERIA-28 found during post-fix
variant audit:
1. _guardrail_modification_check had the same isinstance(dict) bypass
Veria-AI just flagged on the pre-call strip. A caller sending
`{"metadata": "{…}"}` as a JSON-encoded string (multipart/form-data
or extra_body) skipped the guard, got parsed to dict downstream, and
reached guardrail logic with bypass flags intact. Coerce strings via
safe_json_loads before evaluating.
2. The allow_client_tags strip only covered body metadata.tags and
litellm_metadata.tags — caller-supplied tags arriving via the
x-litellm-tags header or root-level data["tags"] bypassed it. Gate
add_request_tag_to_metadata's result on the same flag.
3. requester_metadata was deepcopied BEFORE the strip, so attacker
injections (user_api_key_metadata shadows, disallowed tags,
_pipeline_managed_guardrails) persisted in the snapshot. The PANW
guardrail (and any future consumer) trusting requester_metadata
would see forged values. Move the deepcopy to after the strip.
Regression tests added for each.
|
||
|---|---|---|
| .. | ||
| test_auth_checks.py | ||
| test_auth_exception_handler.py | ||
| test_auth_hot_path_network_requests.py | ||
| test_auth_utils.py | ||
| test_cli_auth.py | ||
| test_custom_auth_end_user_budget.py | ||
| test_handle_jwt.py | ||
| test_info_routes.py | ||
| test_litellm_license.py | ||
| test_login_utils.py | ||
| test_mcp_ip_filtering.py | ||
| test_model_checks_fallbacks.py | ||
| test_model_checks.py | ||
| test_object_permission_loading.py | ||
| test_onboarding.py | ||
| test_organization_budget_enforcement.py | ||
| test_password_hashing.py | ||
| test_route_checks.py | ||
| test_team_member_budget.py | ||
| test_unmapped_model_budget_enforcement.py | ||
| test_user_api_key_auth.py | ||