web-design-expert
Warn
Audited by Snyk on Jun 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required workflow uses Playwright MCP to screenshot arbitrary runtime URLs (e.g.,
url: 'https://frankx.ai'), which causes the agent to ingest browser-extracted page content/prose from that URL into the LLM context, creating an outsider free-text injection surface.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata