gemini
Warn
Audited by Snyk on Sep 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch instructions and parameter schemas from an external markdown file (
https://www.pixazo.ai/models/gemini.md), which constitutes an operational dependency on an unverified third-party domain under the dependency gate.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata