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). This skill navigates to arbitrary URLs and executes/reads page content (nav.js opens user-provided URLs; eval.js runs JavaScript in the page and returns results; pick.js extracts DOM/text/href from the loaded page), so it clearly ingests untrusted third‑party web content that could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:41 AM