baoyu-post-to-weibo
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of system commands to automate browser processes and manage the clipboard. It invokes
powershell.exeon Windows,osascriptandswifton macOS, andxclip,wl-copy,xdotool, orydotoolon Linux. Evidence is found inscripts/copy-to-clipboard.tsandscripts/paste-from-clipboard.tsfor cross-platform support. - [DYNAMIC_EXECUTION]: To handle rich text and images in the clipboard, the skill dynamically constructs and executes Swift source code on macOS and PowerShell commands on Windows. Evidence includes
getMacSwiftClipboardSourceandcopyImageWindowsinscripts/copy-to-clipboard.ts. - [EXTERNAL_DOWNLOADS]: The skill depends on third-party packages
baoyu-chrome-cdpandbaoyu-mdfor its core operations, and its execution instructions involve usingnpx -y bunto provide the runtime environment. Evidence is inscripts/package.jsonandSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill ingests arbitrary text and Markdown files provided by the user to generate social media posts.
-
- Ingestion points: Markdown and plain text arguments in
weibo-post.tsandweibo-article.ts.
- Ingestion points: Markdown and plain text arguments in
-
- Boundary markers: None identified in the input processing scripts.
-
- Capability inventory: Significant capabilities including system command execution (
spawnSync) and browser script execution (Runtime.evaluate).
- Capability inventory: Significant capabilities including system command execution (
-
- Sanitization: Uses
JSON.stringifyto escape content before inserting it into the browser context, which mitigates direct script injection into the Weibo editor.
- Sanitization: Uses
Audit Metadata