baoyu-post-to-wechat

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of spawn, spawnSync, and execSync to run external processes. This includes running its own sub-scripts via npx and bun, as well as invoking system-level utilities for UI automation.
  • [COMMAND_EXECUTION]: To handle clipboard operations across different operating systems, the skill uses osascript on macOS, powershell.exe (SendKeys) on Windows, and xdotool/ydotool on Linux to simulate real keystrokes (e.g., Cmd+V/Ctrl+V), which helps in bypassing synthetic event detection on websites.
  • [EXTERNAL_DOWNLOADS]: The markdown rendering component dynamically fetches syntax highlighting language files from an external CDN (cdn-doocs.oss-cn-shenzhen.aliyuncs.com) and interacts with the PlantUML server (www.plantuml.com) for diagram generation. Additionally, the skill can download images from remote URLs if they are referenced in the provided markdown articles.
  • [COMMAND_EXECUTION]: The skill automates browser interactions by launching Google Chrome with remote debugging enabled and sending commands via the Chrome DevTools Protocol (CDP), including script evaluation and DOM manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 03:19 AM
Security Audit — agent-trust-hub — baoyu-post-to-wechat