claude-md-generator
Warn
Audited by Snyk on May 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill makes a runtime POST to the Gemini API endpoint (https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY), using the model's returned text to generate the CLAUDE.md (remote content directly controls the agent's output) and the skill requires a GEMINI_API_KEY.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata