stitch-design
Warn
Audited by Snyk on May 20, 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). The skill's required workflow (Step 5 "Process Exported Code" and the "Sharing with Claude" instructions in references/export-guide.md) expects the agent to ingest and interpret exported HTML/CSS or a Figma link originating from Google Stitch (stitch.withgoogle.com), which is untrusted third-party user-generated content that directly influences integration and next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata