browser-pilot
Fail
Audited by Snyk on Feb 15, 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 directly embed sensitive values into CLI commands (e.g., fill --text Password -v ) and supports cookie control/login automation, which requires the agent to place secrets verbatim into command arguments or outputs, creating an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill explicitly navigates to and scrapes arbitrary public websites (e.g., the "node .browser-pilot/bp navigate -u " and extract/content commands) so the agent will fetch and interpret untrusted third-party web/user-generated content that could enable indirect prompt injection.
Audit Metadata