browser-visible
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing guidance on how to use the 'browser_use' tool with specific parameters. It does not introduce new code, dependencies, or network operations.
- [DATA_EXFILTRATION]: No exfiltration patterns detected. While the skill mentions handling logins and CAPTCHAs, it specifies these as manual tasks for the user within a visible window, which increases user oversight of the agent's activities.
- [PROMPT_INJECTION]: The instructions are clear and follow standard operational patterns for agent skills. There are no attempts to override safety filters or bypass system instructions.
- [INDIRECT_PROMPT_INJECTION]: Although the skill enables processing of external web content, the use of a visible browser window (headed mode) acts as a transparency measure, allowing the user to monitor page interactions and detect potential malicious content on websites being visited.
Audit Metadata