documentation-lookup
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by retrieving and processing content from an external documentation provider.
- Ingestion points: Documentation and code snippets fetched via the
query-docstool inSKILL.md. - Boundary markers: Absent; the instructions do not specify delimiters or provide guidance to the agent to treat the fetched content as untrusted data.
- Capability inventory: The agent uses the external data to generate technical responses and provide executable code examples.
- Sanitization: No specific sanitization or filtering of the fetched documentation content is defined.
- [DATA_EXFILTRATION]: User queries are sent to the Context7 MCP service to resolve library identifiers and retrieve documentation. The skill includes a 'Best Practices' section advising the agent to redact sensitive information such as API keys and tokens before transmission.
Audit Metadata