context7-mcp
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data retrieved via specialized tools.
- Ingestion points: Content is fetched from external documentation services and GitHub repositories through the
query-docsandquery-codetools in SKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to separate fetched documentation from the agent's primary instructions, nor are there warnings to ignore embedded commands within the retrieved data.
- Capability inventory: The skill enables the agent to read arbitrary files from public repositories and documentation, which could be used to influence the agent's behavior if those files contain adversarial text.
- Sanitization: The skill does not implement or require sanitization of the fetched documentation before it is incorporated into the agent's response context.
Audit Metadata