screenshot

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run to execute platform-specific screenshot utilities like screencapture, scrot, and gnome-screenshot. These calls are implemented using list-based arguments to prevent command injection.
  • [SAFE]: The skill includes bundled Swift and PowerShell scripts to interact with native OS APIs for window and display discovery. All logic is contained within the skill package, and no remote code downloads are performed.
  • [SAFE]: No sensitive data access, exfiltration patterns, or obfuscated payloads were detected in the source code or instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 12:05 AM
Security Audit — agent-trust-hub — screenshot