frontend-design
Warn
Audited by Snyk on Apr 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill's provided image-generation workflow (scripts/generate_images.py) injects a GoogleSearch tool into the Gemini generation call (types.Tool(googleSearch=types.GoogleSearch())), and SKILL.md explicitly instructs running that script for asset generation, meaning the agent can fetch and read untrusted open-web search results at runtime which could materially influence model actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata