design-context-extract
Warn
Audited by Snyk on May 14, 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 explicitly fetches and analyzes live URLs ("For URLs: ... WebFetch the URL and analyze HTML/CSS" and "call build_site(prompt=<url + extraction goal>)") and then uses extracted HTML/CSS/design tokens to drive recommendations and outputs, so untrusted third-party webpage content can be read/interpreted and materially influence the agent's decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata