browser-use

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates a browser agent that processes untrusted external web content, creating a surface for indirect prompt injection where malicious instructions on a website could attempt to redirect the agent's behavior.
  • Ingestion points: Web pages accessed via the browser-use Python agent or CLI as described in references/operation.md.
  • Boundary markers: The skill includes explicit instructions in SKILL.md to treat web content as untrusted and to never follow instructions found on pages that deviate from the user's task.
  • Capability inventory: The skill uses the Bash tool and the browser-use library, which can perform network requests, file system operations (via the agent), and browser automation.
  • Sanitization: The instructions warn that credential-redaction features are not security sandboxes and that all agent-generated content and page data must be verified.
  • [EXTERNAL_DOWNLOADS]: The skill documentation guides the user to install the browser-use Python package and CLI from official registries.
  • Evidence: References to uv tool install browser-use==1.0.3 and pip install patterns in references/operation.md.
  • [COMMAND_EXECUTION]: The skill executes a local Python script for metadata inspection and provides instructions for running CLI commands.
  • Evidence: The instruction to run python3 "$SKILL_DIR/scripts/preflight.py" in SKILL.md. The script itself was analyzed and found to be a safe metadata check using importlib.metadata and shutil.which without network or write access.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 05:08 AM