visual-verdict
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or data exfiltration vectors were detected.
- [COMMAND_EXECUTION]: The skill mentions using standard shell commands (e.g.,
cp) for managing local screenshot files and baselines. These operations are within the expected scope of a UI development and testing workflow. - [EXTERNAL_DOWNLOADS]: No automated downloads of external scripts or binaries are performed. The skill interacts with user-provided URLs and local files for comparison.
- [DATA_EXPOSURE]: The skill operates on local UI components and standard design files. It does not attempt to access sensitive system files or credentials.
Audit Metadata