agent-browser
Fail
Audited by Snyk on Mar 18, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt contains explicit examples and commands that embed credentials inline (e.g., proxy URLs with user:pass,
agent-browser set credentials user pass, cookie set/copy patterns and plaintext form passwords), meaning an agent generating those commands would need to include secret values verbatim.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). This skill explicitly opens arbitrary URLs and ingests page content (SKILL.md "agent-browser open ", snapshot/get html/get text) and even executes page-provided JavaScript/test-seam commands (many "agent-browser eval "window.TEST.commands..."" examples in SKILL.md and references/phaser-testing.md), so untrusted third‑party pages can supply content or functions that the agent reads and acts on.
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata