documentation-lookup
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- PROMPT_INJECTION (SAFE): The skill demonstrates a surface for indirect prompt injection as it retrieves and processes external documentation content. 1. Ingestion points: documentation content retrieved via the query-docs tool. 2. Boundary markers: Absent; there are no instructions to the agent to disregard instructions within the fetched text. 3. Capability inventory: documentation resolution and retrieval (resolve-library-id, query-docs). 4. Sanitization: Absent. The finding is marked SAFE as the vulnerability surface is inherent to the primary intended documentation-lookup functionality.
- NO_CODE (SAFE): The skill consists entirely of markdown instructions and does not include any accompanying scripts, executables, or package dependencies.
Audit Metadata