context7
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions utilize
curlandjqto perform network requests and process JSON data from the Context7 API. These are standard system utilities used within the skill's defined workflow for data retrieval. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest documentation content from a third-party API (context7.com), creating a vulnerability surface where malicious instructions could be embedded in the retrieved data.
- Ingestion points: External documentation fetched via the
/api/v2/contextendpoint as described inSKILL.md. - Boundary markers: None identified. The skill does not provide instructions to wrap the external content in delimiters or warn the agent to ignore instructions within the retrieved documentation.
- Capability inventory: The skill uses
curlfor network operations andjqfor output formatting. - Sanitization: There is no evidence of sanitization, filtering, or validation of the fetched documentation before it is presented to the agent.
Audit Metadata