web-access

Warn

Audited by Snyk on Mar 24, 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 opens and reads arbitrary public web pages (including social media like 小红书/微博/X) as part of its required workflow—see SKILL.md ("何时使用", "能力" and examples) and the CDP proxy API in scripts/cdp-proxy.mjs which expose /new?url, /navigate, /eval, /click, /screenshot endpoints that ingest and let the agent interpret third‑party page content to decide next actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 24, 2026, 03:17 PM
Issues
1