Skills
Navigate
skills/jasoft/ursoft-skills/wechat-send/Gen Agent Trust Hub

wechat-send

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run to execute various macOS system utilities including osascript, pbcopy, pgrep, and open. These are used to control the WeChat application, check process status, and manage clipboard contents in scripts/wechat_auto.py.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input which constitutes a vulnerability surface.
  • Ingestion points: The contact and message arguments in scripts/wechat_auto.py.
  • Boundary markers: None present.
  • Capability inventory: Subprocess calls to system utilities (osascript, pbcopy, pgrep, open) throughout the automation scripts.
  • Sanitization: The skill implements a robust design by piping user input to pbcopy via standard input and using UI-level 'Paste' commands via AppleScript, effectively preventing shell injection or direct command interpolation of untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 04:14 AM