wewrite-wechat-ai-publishing

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow scrapes public trending topics and search suggestions from social and search platforms (Weibo, Toutiao, Baidu) which contain outsider-authored free text ingested by the agent during hotspot fetching and topic selection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning an external repository from GitHub during installation, constituting an unverified third-party operational dependency.