browser-automation

Warn

Audited by Snyk on Mar 4, 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). SKILL.md explicitly exposes the agent to arbitrary web pages via browser_navigate and browser_extract (which auto-scrolls and collects page data), meaning the agent will ingest untrusted public web content whose text could influence subsequent browser_act decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 01:01 AM