wechat-draft-publisher
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill manages WeChat API credentials (AppID and AppSecret) by storing them in a local configuration file (~/.wechat-publisher/config.json). It follows security best practices by recommending and applying restricted file permissions (chmod 600) to protect these credentials from other users on the system.
- [EXTERNAL_DOWNLOADS]: The skill requires the 'requests' library for communicating with the WeChat API. This is a standard, well-known dependency in the Python ecosystem and is fetched from the official Python Package Index (PyPI).
- [COMMAND_EXECUTION]: The skill invokes local Python scripts to process HTML and interact with the WeChat API. This execution is scoped to the skill's specific functionality and does not include mechanisms for arbitrary shell command injection.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted HTML data. Ingestion Point: Content file read in publisher.py. Boundary Markers: Absent in raw content, but JSON structure is used for transmission. Capability Inventory: Network POST to api.weixin.qq.com and local file I/O in publisher.py. Sanitization: json.dumps ensures safe interpolation into the API request.
- [SAFE]: The skill's network activity is restricted to communication with official WeChat API endpoints (api.weixin.qq.com) for the purpose of draft publication and image uploading.
Audit Metadata