claude-chrome
Warn
Audited by Snyk on Feb 15, 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 controls a real Chrome browser and explicitly navigates arbitrary public URLs and reads/extracts page content/DOM (see "Browser Capabilities: Read page content and DOM" and examples like "competitor scan", "Go to the product listings page", and "research LinkedIn profiles"), so it ingests untrusted third‑party/user‑generated web content into the agent's workflow.
Audit Metadata