context7-mcp

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and does not contain any executable code, hardcoded credentials, or obfuscated payloads. It follows standard patterns for a Retrieval-Augmented Generation (RAG) assistant.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by design, as it retrieves and processes external documentation. This is a characteristic of information-retrieval skills rather than a vulnerability.
  • Ingestion points: External documentation is ingested via the query-docs tool calls described in the skill instructions.
  • Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the retrieved content.
  • Capability inventory: No local scripts, subprocesses, or system-level capabilities are defined within this skill.
  • Sanitization: No filtering or sanitization of the external content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 08:49 AM
Security Audit — agent-trust-hub — context7-mcp