context7-auto-research

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill installation instructions point to npx skills add -g BenedictKing/context7-auto-research. This repository is hosted by an untrusted GitHub user not included in the trusted organizations list. Contents of such repositories are unvetted and could be modified to include malicious code.
  • [PROMPT_INJECTION] (LOW): The skill fetches documentation from the Context7 API. This external data ingestion represents an Indirect Prompt Injection surface. Mandatory Evidence Chain: 1. Ingestion points: External content via Context7 API. 2. Boundary markers: No delimiters or ignore-instructions warnings found in the manifest. 3. Capability inventory: Documentation retrieval for AI context. 4. Sanitization: No evidence of validation or sanitization of external data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:30 PM