Commit Graph
2 Commits
Author SHA1 Message Date
Devam Shah d28c4b4b1e feat: config-pluggable refusal classifiers and leak detectors
PIIDetector and SandboxEscapeDetector were wired directly in
probe_actor/refusal.py and the refusal classifier manager was populated from
a hardcoded list, so the only way to toggle a bundled detector or add an
organization-specific signature was to patch the module.

Add a DetectorRegistry mapping plugin names to factories, assembled from an
agentic_security.toml [detectors] section via build_from_config. Custom
detectors load by import path ("pkg.module:ClassName"). refusal.py gains
build_refusal_manager(config=None) reading the [detectors] table; all public
symbols are preserved. Built-in leak detectors ship registered but disabled,
so default refusal_heuristic behaviour is unchanged.

Closes #82

Signed-off-by: Devam Shah <devamshah91@gmail.com>
2026-06-22 19:40:33 +05:30
Devam Shah dd59704fdf fix: wildcard CORS + credentials spec violation, path-traversal guard on /icons proxy
CORS: drop allow_credentials=True. With allow_origins=['*'] Starlette reflects
the request Origin and emits Access-Control-Allow-Credentials: true on any
credentialed request — a reflect-any-origin hole. The app authenticates with
Bearer tokens in the Authorization header, so credentialed CORS was never needed.

/icons/{icon_name}: validate against a strict allowlist (re.fullmatch
[A-Za-z0-9._-]+\.png) and assert the resolved path stays inside ICONS_DIR before
any filesystem write or outbound fetch. Closes the path-traversal / arbitrary-write
(CWE-22) and controlled-URL (CWE-73) surface on the unsanitized icon_name.

Adds CORS middleware tests and icon-name validation tests (traversal, encoded
slash, null byte, trailing newline, wrong extension).

Closes #298

Signed-off-by: Devam Shah <devamshah91@gmail.com>
2026-06-22 10:10:43 +05:30