context7
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [Prompt Injection] (LOW): The skill facilitates data ingestion from an external source, creating an indirect prompt injection surface. * Ingestion points: Data enters via search and context API endpoints at context7.com. * Boundary markers: Absent; no delimiters are defined to isolate external documentation from agent instructions. * Capability inventory: The skill is limited to curl for network retrieval and jq for parsing; no dangerous file-system or code execution capabilities are present. * Sanitization: Absent; documentation content is processed without filtering or escaping.
- [External Downloads] (LOW): The skill performs network requests via curl to context7.com, a third-party domain not included in the trusted source whitelist.
Audit Metadata