agent-browser

Warn

Audited by Snyk on Feb 27, 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 skill explicitly wraps a headless browser and instructs the agent to "open ", "snapshot", and "get text" (see SKILL.md and README.md examples like agent-browser open google.com, agent-browser snapshot -i, and agent-browser get text @e1), which causes the agent to fetch and interpret arbitrary public web pages whose user-generated/untrusted content could influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 06:23 PM