wechat-studio
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements its documented features using standard Node.js practices and well-known libraries like 'marked' and 'sharp'. No malicious behaviors were detected during the analysis of the 27 files.
- [DATA_EXFILTRATION]: Network operations are restricted to the official WeChat API domain (api.weixin.qq.com) and user-provided image URLs. Sensitive credentials (AppID and Secret) are managed through standard environment variables or local configuration files without exposure to unauthorized external parties.
- [PROMPT_INJECTION]: While the skill uses AI-driven writing and text-humanization features (Dan Koe style and Humanizer-zh), these are implemented as structured templates designed to guide the model's output rather than override its safety or operational guidelines.
- [COMMAND_EXECUTION]: The skill executes local scripts for content processing. The scripts perform file I/O and network requests necessary for their stated purpose, such as image compression and API interaction, without invoking arbitrary shell commands or downloading untrusted executables.
Audit Metadata