search
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill routes to external search tools (Exa, OpenAI Web Search, Context7 CLI) to ingest content into the agent context.
- Ingestion points: Technical documentation retrieved via Context7 and general web content from Exa and OpenAI Web Search.
- Boundary markers: The instructions do not define delimiters or ignore-instruction warnings for processed data.
- Capability inventory: The skill enables the agent to fetch remote content and use it to synthesize answers.
- Sanitization: No data validation or sanitization of external content is specified.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the Context7 CLI to query technical documentation for libraries, frameworks, and APIs.
Audit Metadata