wechat-article-studio
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill follows secure secret management practices. It explicitly instructs the agent to retrieve the
WECHAT_ACCESS_TOKEN,WECHAT_APP_ID, andWECHAT_APP_SECRETfrom environment variables only, with strict prohibitions against writing these credentials to files, logs, or payload previews. - [EXTERNAL_DOWNLOADS]: The skill's publishing utility (
publish_wechat_draft.py) communicates with the well-known WeChat API (api.weixin.qq.com). These network operations are standard for the skill's primary function of uploading media and managing article drafts. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a content processor for external 'materials', 'source folders', and 'Markdown manuscripts'. While it directs the agent to prioritize facts and brand consistency, it does not explicitly define delimiters or sanitization logic for these external inputs, which constitutes a minor surface for indirect prompt injection common to content-generation tools.
Audit Metadata