kernel-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: 0.90). The skill explicitly instructs the agent to open arbitrary public websites (e.g., using "agent-browser -p kernel open "), take snapshots and read page content ("agent-browser -p kernel snapshot -i", wait --text, get url), and create site-specific skills for public domains (examples: kroger.com, amazon.com), so it ingests and interprets untrusted third‑party web content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:55 PM