documentation-lookup

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits user-provided queries to the Context7 MCP server to resolve library IDs and fetch documentation snippets. While this is the intended functionality, it involves external data transmission.
  • Evidence: The resolve-library-id and query-docs tools take the user's full question as a query parameter.
  • Mitigation: The skill explicitly instructs the agent to redact API keys, passwords, and tokens before sending queries to Context7.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by incorporating third-party documentation content into the agent context.
  • Ingestion points: Documentation text and code snippets returned by the query-docs tool.
  • Boundary markers: No delimiters or instructions to ignore embedded commands are specified for the incoming documentation content.
  • Capability inventory: This skill does not explicitly define system-level capabilities like file writing or code execution.
  • Sanitization: No validation or filtering is performed on the documentation content fetched from the external source.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 04:01 AM
Security Audit — agent-trust-hub — documentation-lookup