wechat-message

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts scripts/wechat_automation_script.applescript and scripts/wechat_automation_script.ps1 download image files from user-supplied URLs using curl and Invoke-WebRequest respectively.
  • [COMMAND_EXECUTION]: The macOS script utilizes do shell script to execute various system commands including curl for downloads, mktemp for temporary directory creation, rm for cleanup, and sips for image processing. It also relies on the external cliclick utility for mouse automation.
  • [DYNAMIC_EXECUTION]: The Windows PowerShell script uses Add-Type to dynamically compile C# code for P/Invoke, enabling access to Win32 API functions in user32.dll for window management and mouse events.
  • [PRIVILEGE_ESCALATION]: The skill requires the user to manually grant 'Accessibility' permissions to their terminal or application environment in macOS System Settings. This permission allows the script's System Events commands to interact with and control the WeChat user interface.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts message content and contact names from the agent's context. While it uses proper quoting for shell commands, if the agent receives instructions from an untrusted external source to send a message, the skill will execute that automation as requested. Boundary markers are not explicitly defined for the message payload.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 01:29 AM