proxyuser
Warn
Audited by Snyk on May 4, 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 workflow (SKILL.md) instructs ProxyUser to browse arbitrary public target URLs and scenario URLs (e.g., the run_all endpoint with "target_url": "https://preview-abc123.vercel.app" and scenario "url" fields) and consumes returned AI diagnoses/video derived from those pages, so untrusted third‑party site content can influence the agent's decisions and tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata