dev-browser
Warn
Audited by Snyk on Feb 16, 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 automates browsing and scraping of arbitrary public websites and APIs (e.g., page.goto, client.getAISnapshot/selectSnapshotRef, page.evaluate(fetch) and the scraping guide references/scraping.md that captures responses and replays API requests, plus FlareSolverr solveUrl/bypassCloudflare), so the agent will fetch and read untrusted third‑party web content as part of its workflow.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill auto-enables "stealth" anti-detection and Cloudflare-bypass features and auto-installs packages / starts Docker containers, which instructs the agent to evade remote security protections and modify the host environment rather than staying read-only.
Audit Metadata