browser-use

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform browser automation tasks using npx mcporter commands.
  • [EXTERNAL_DOWNLOADS]: Use of npx to execute mcporter may result in the package being downloaded from the npm registry.
  • [SAFE]: The skill interacts with external web content, which is a surface for indirect prompt injection. This risk is inherent to browser automation.
  • Ingestion points: Web data is retrieved using take_snapshot and evaluate_script in SKILL.md.
  • Boundary markers: None explicitly defined in the file.
  • Capability inventory: The skill allows for navigation, element interaction (click/fill), and script evaluation.
  • Sanitization: The skill contains clear instructions for the agent to avoid outputting sensitive data like tokens or passwords.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 03:59 PM
Security Audit — agent-trust-hub — browser-use