stitch-react
Warn
Audited by Snyk on Aug 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow ingests Stitch-generated HTML via the Stitch MCP
prefix:get_screencall (stored assource.html) and then parses that HTML for token extraction and component generation, meaning attacker-supplied free text can enter through the Stitch screen content without requiring a prior item selection beyond having a screen.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata