context7-skill-generator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill extracts content from external tools and conversation history to create new system instructions.
- Ingestion points: Tool results from
resolve-library-idandquery-docswithin fileSKILL.md. - Boundary markers: The skill does not implement boundary markers or 'ignore' instructions to separate documentation content from agent instructions.
- Capability inventory: File-write capability to the
plugins/directory to create newSKILL.mdfiles. - Sanitization: No evidence of sanitization for natural language instructions; the 'Smart Formatting' logic only addresses markdown structure and syntax.
- [COMMAND_EXECUTION] (SAFE): The skill writes files to the local filesystem at
plugins/{plugin-name}/skills/{skill-name}/SKILL.md. This is the primary intended function and is controlled via user-prompted metadata.
Audit Metadata