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's SKILL.md explicitly instructs the agent to navigate arbitrary URLs (e.g., page.goto examples), use getAISnapshot/selectSnapshotRef to read page content, and scrape/interact with third‑party websites (see "Scraping Data" and "Writing Scripts"), so it will fetch and interpret untrusted public web content that can change subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 07:09 AM