context7
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [Data Exposure & Exfiltration] (LOW): The skill performs network requests via
curltohttps://context7.com, which is not a whitelisted domain. It transmits user-provided search terms and library names to this external service. - [Indirect Prompt Injection] (LOW): The skill ingests untrusted text data from an external API, creating a surface for potential instruction injection if the source documentation is compromised.
- Ingestion points: Documentation snippets fetched via the
/api/v2/contextendpoint. - Boundary markers: Absent; the agent is not instructed to treat the fetched content as potentially untrusted data.
- Capability inventory: Uses
curlfor network requests andjqfor JSON processing. - Sanitization: None; the raw text or JSON results are passed back to the agent for processing.
Audit Metadata