stitch-design-md
Warn
Audited by Snyk on Apr 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and parse project assets (htmlCode.downloadUrl and screenshot.downloadUrl) from the Stitch MCP server using web_fetch/read_url_content, which are user/project-provided HTML/images that the agent must read and use to drive synthesized DESIGN.md and subsequent stitch prompts, so untrusted third‑party content can materially influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata