context7
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill utilizes curl and jq to process API requests and responses. This is standard for utility skills but requires the agent to have command execution capabilities.
- [EXTERNAL_DOWNLOADS] (LOW): The skill connects to context7.com to fetch data. There is no evidence of downloading executable code or scripts.
- [PROMPT_INJECTION] (LOW): Ingests untrusted external documentation which could lead to Indirect Prompt Injection. 1. Ingestion points: API responses from context7.com (Step 2). 2. Boundary markers: Absent. 3. Capability inventory: curl, jq in SKILL.md workflows. 4. Sanitization: Absent.
Audit Metadata