diagnose-ppr
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: 0.90). The skill instructs the agent-browser to load and interact with an arbitrary target page URL (see steps 2–6:
agent-browser get/open, screenshots,snapshot, andreact suspense), and then reads and interprets that page's DOM/Suspense output to grade and decide actions, so untrusted third‑party page content can influence the agent's analysis and behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata