analyze-design
Warn
Audited by Snyk on Jun 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Step 3–7 ingest outsider-authored free text indirectly from the design itself: the adapter opens a user-supplied Figma URL and then reads the document’s layout/screenshot-derived properties via MCP calls (e.g.,
__snapshot_layout,__get_style_guide,__get_variables), which can contain arbitrary text authored by third parties in the design.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata