documentation-lookup
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses pre-configured MCP tools for its primary functionality and does not contain any malicious code, obfuscation, or direct remote code execution patterns.\n- [DATA_EXPOSURE_AND_EXFILTRATION]: The instructions include a specific best practice requiring the agent to redact API keys, passwords, tokens, and other secrets from any query sent to the external documentation service (Context7), mitigating the risk of accidental credential exposure.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied questions to fetch documentation, which introduces an indirect injection surface.\n
- Ingestion points: User's full question is passed as a parameter to the
resolve-library-idandquery-docstools (SKILL.md).\n - Boundary markers: No explicit XML tags or delimiters are defined for the interpolated user query.\n
- Capability inventory: The skill is limited to documentation retrieval via tool calls and does not have access to shell execution, file system writes, or network requests outside the specific tools provided.\n
- Sanitization: The skill includes an explicit instruction to redact secrets before processing user input.
Audit Metadata