NYC

agent-browser

Warn

Audited by Snyk on Feb 15, 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 agent-browser skill explicitly navigates to arbitrary URLs with the "open " command and returns page accessibility snapshots via "snapshot" that the agent is expected to parse, thereby exposing the agent to untrusted public web content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:08 PM