agent-browser
Warn
Audited by Snyk on Mar 9, 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 navigates to arbitrary URLs (e.g., "agent-browser open " in SKILL.md and references/commands.md) and instructs AI agents to parse snapshots of live pages ("agent-browser snapshot -i --json # AI parses tree and refs" in SKILL.md) so untrusted third‑party page content is fetched and interpreted to decide actions.
Audit Metadata