weixin-official-account-operator

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

• Third-party content exposure detected (medium risk: 0.30). The workflow requires reading private WeChat messages and follower inboxes via tools like weixin_oa_list_recent_messages and weixin_oa_list_followers, which ingest outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains an explicit runtime installation command pointing to an external GitHub repository (npx skills add YunGroAI/agent-skills --skill yungroai-skills), which acts as an operational dependency providing setup instructions and checking behaviors, satisfying the criteria for a weak/unknown/suspicious runtime external dependency.