context7
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves documentation context from the external Context7 API (context7.com) and presents it directly to the agent. This represents an indirect prompt injection surface where malicious instructions could theoretically be embedded in the retrieved content to target the AI agent.
- Ingestion points: Data is fetched via HTTP requests in
scripts/context7.pyand printed to the standard output for agent consumption. - Boundary markers: The skill does not implement delimiters or safety instructions to wrap the retrieved external content.
- Capability inventory: While the skill script itself only performs network reads, it is designed for use in an environment where the agent likely possesses broader system capabilities such as file access or command execution.
- Sanitization: No sanitization, filtering, or validation is performed on the content returned by the API before it enters the agent's context.
Audit Metadata