dev-browser
Warn
Audited by Snyk on Feb 25, 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 automates browsing and scraping of arbitrary public websites (see SKILL.md scripts using page.goto and the ARIA snapshot APIs) and the references/scraping.md guide shows capturing page responses (page.on("response")) and replaying API requests via page.evaluate(fetch) against public endpoints (e.g., social media /api/ or UserTweets), so untrusted, user-generated third‑party content is fetched, parsed, and used to drive subsequent tool actions.
Audit Metadata