sqsl-article-to-wechat
Warn
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [DYNAMIC_EXECUTION]: The script
scripts/render_wechat_html.pydynamically scans and loads Python modules from thestyles/folder in the current working directory usingimportlib.util. This allows for the execution of arbitrary Python code if malicious scripts are present in the environment where the skill is run. - [COMMAND_EXECUTION]: Multiple scripts (
render_wechat_html.py,wechat_draft_publisher.py, andstyles/style_olive_artisan.py) usesubprocess.runto invoke Google Chrome in headless mode. While the commands are constructed as lists to avoid shell injection, this creates a dependency on an external binary and executes it with local file paths as arguments. - [DATA_EXFILTRATION]: The skill is designed to transmit article content, images, and WeChat API credentials (
app_id,app_secret) to the official WeChat API endpoints (api.weixin.qq.com). While this is the core functionality, users should be aware that sensitive content and credentials are sent to an external service.
Audit Metadata