dev-browser

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: 0.90). The dev-browser skill explicitly navigates and scrapes arbitrary public websites and APIs (see SKILL.md examples using page.goto and the client.getAISnapshot API) and the references/scraping.md shows capturing and replaying responses from public endpoints (e.g., "UserTweets" /api captures), meaning the agent will ingest untrusted, user-generated third‑party content and parse/interpret it as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:32 PM