skills/letta-ai/skills/screenshot/Gen Agent Trust Hub

screenshot

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Spawns system screenshot utilities (screencapture, scrot, gnome-screenshot, import, osascript) via subprocess.run(). This is standard, safe, and necessary operational logic aligned with the skill's primary function of capturing user-requested screenshots.
  • [PRIVILEGE_ESCALATION]: Mention of 'escalated permissions' in documentation only exists as guidance for handling potential sandbox/macOS Screen Recording approval blockages, not as embedded exploit code or unsafe automated invocation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:45 PM
Security Audit — agent-trust-hub — screenshot