context7
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlandjqto interact with the Context7 API as documented inSKILL.mdandREADME.md. These commands are standard for the skill's documentation-fetching purpose.\n- [EXTERNAL_DOWNLOADS]: Documentation data is retrieved from the external domainhttps://context7.com. This is the core functionality of the skill.\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection (Category 8) as it integrates external content into the agent's context.\n - Ingestion points: Data is fetched from
https://context7.com/api/v2/context(SKILL.md).\n - Boundary markers: No delimiters or safety instructions are provided to the agent for handling the external content.\n
- Capability inventory: The skill uses
curlandjqfor data retrieval and processing (SKILL.md).\n - Sanitization: There is no evidence of content sanitization before the external documentation is presented to the agent.
Audit Metadata