agent-browser

Warn

Audited by Snyk on Feb 19, 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 instructs the agent to open and snapshot arbitrary target URLs (e.g., "agent-browser open " and the SKILL.md/quick-start steps to open pages and produce JSON snapshots), so it fetches and ingests untrusted public web content that can influence subsequent interactions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 05:18 PM