web-access
Warn
Audited by Snyk on Mar 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and browses arbitrary public URLs and executes/reads their content to drive actions (see SKILL.md and README examples like "读一下这个页面：[URL]" and the CDP proxy endpoints in scripts/cdp-proxy.mjs such as /new?url and /eval that ingest page content/JS), so untrusted third‑party pages can influence agent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata