content-source-router
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a routing mechanism that evaluates external signals, including inbound request paths and query string parameters (
source_hint), to dispatch content-fetch tasks. - Ingestion points: Found in
SKILL.mdunder the 'Routing Rules' section, where Priority 2 (Inbound request path) and Priority 4 (Explicitsource_hintin query string) are identified as valid inputs for the router. - Boundary markers: The instructions do not specify boundary markers or explicit validation protocols to prevent malicious instructions embedded in these signals from influencing the agent's behavior during routing.
- Capability inventory: The skill enables the
ReadandGreptools, which allow the agent to traverse the local file system (e.g.,lib/content/router.ts) and access repository data. - Sanitization: The skill lacks documentation regarding the sanitization or escaping of external inputs before they are processed by the router implementation.
Audit Metadata