stitch-mcp-cli
Warn
Audited by Snyk on May 17, 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 documented tools (e.g., build_site, get_screen_code, serve) explicitly fetch HTML/CSS and screenshots from Stitch projects via the Stitch API ("Fetch HTML/CSS for each screen", tool examples and patterns in SKILL.md), which are user-generated/third‑party design content that the agent is expected to read, interpret, and act on (site generation, integration, analysis), so that untrusted content could materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata