skills/jetbrains/skills/screenshot/Gen Agent Trust Hub

screenshot

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run in Python and P/Invoke in PowerShell to execute OS-native screenshot tools like screencapture, scrot, and gnome-screenshot.
  • [PRIVILEGE_ESCALATION]: Documentation encourages the use of escalated permissions and employs the -ExecutionPolicy Bypass flag for PowerShell execution to circumvent system security restrictions.
  • [DYNAMIC_EXECUTION]: Helper scripts for macOS are executed dynamically at runtime using the swift interpreter to access system-level window and permission information.
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-supplied application names and window titles into shell commands with insufficient sanitization, creating a potential injection vector.
  • Ingestion points: Input arguments for application names (--app) and window titles (--window-name) in take_screenshot.py.
  • Boundary markers: Absent; there are no delimiters protecting the command context from malicious inputs.
  • Capability inventory: The skill can execute shell commands (osascript, screencapture) and write files to user-defined paths.
  • Sanitization: Employs minimal double-quote escaping in take_screenshot.py, which may not prevent all forms of AppleScript injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:24 PM