context7

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks common to tools that ingest external data. It retrieves documentation and code snippets from a remote API and provides them to the agent.
  • Ingestion points: Data is ingested through the resolve-library-id and query-docs tools in app.py, which fetch content from https://mcp.context7.com/mcp.
  • Boundary markers: The skill does not implement explicit boundary markers or 'ignore embedded instruction' warnings when passing external content back to the agent.
  • Capability inventory: The skill's capabilities are limited to network communication with the specific Context7 API endpoint and local JSON processing.
  • Sanitization: While the tool performs JSON parsing and error handling, it does not sanitize the retrieved natural language text for potential instruction-based attacks.
  • [DATA_EXFILTRATION]: The skill transmits user queries to the external domain mcp.context7.com. This is the documented primary purpose of the skill and is required for functionality.
  • The author has included explicit warnings in SKILL.md and the tool parameter descriptions advising users not to include sensitive or confidential information in their queries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 09:24 AM