computer-control

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the OS display using xdotool, scrot, and xclip via a display toolkit. These commands are necessary for the skill's primary purpose of GUI automation.
  • [DATA_EXFILTRATION]: The skill captures screenshots of the desktop environment. This introduces a risk of exposure for any sensitive data visible on the screen. The author mitigates this through extensive safety documentation advising on sandboxing and credential hygiene.
  • [SAFE]: No malicious patterns such as obfuscation, hidden URLs, or unauthorized network activity were detected. The implementation follows standard practices for the Claude Computer Use beta feature.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 06:31 PM