browser-use
Fail
Audited by Snyk on Feb 20, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly supports passing secrets as literal command-line metadata (--secret key=value) and describes exporting/syncing cookies and profiles (which include session tokens), which requires accepting and forwarding secret values verbatim.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly supports opening arbitrary URLs and extracting/execing page content (e.g., "browser-use open ", "browser-use get html", "browser-use get text", and remote agent runs like
browser-use -b remote run "Search for AI news..."with --start-url), so the agent will fetch and interpret untrusted public web content that can influence its subsequent actions.
Audit Metadata