browser
Fail
Audited by Snyk on Feb 16, 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 includes examples that embed plaintext credentials directly in commands (e.g., agent-browser fill @e3 "password123"), which instructs the agent to include secret values verbatim and poses a high exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill directly allows the agent to navigate to arbitrary URLs (agent-browser open ) and to snapshot/inspect page content (agent-browser snapshot, get text, get html, get attr), which clearly ingests untrusted public web/user-generated content and exposes the agent to indirect prompt injection.
Audit Metadata