lib-docs
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
WebFetchtool to retrieve documentation from external websites and GitHub wikis. This creates an attack surface where content from a third-party site could contain hidden instructions designed to manipulate the agent's behavior. - Ingestion points: External documentation URLs retrieved via
WebFetchas described in the workflow (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the content fetched from the web.
- Capability inventory: The skill uses
WebSearch,WebFetch, andReadtools. - Sanitization: There is no evidence of filtering or sanitizing the retrieved documentation content before the agent processes and summarizes it.
Audit Metadata