wecomcli-doc

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly performs runtime fetches of document content from doc.weixin.qq.com (e.g., https://doc.weixin.qq.com/doc/* and https://doc.weixin.qq.com/smartpage/* via get_doc_content and smartpage_export_task) and injects the returned Markdown into the agent flow, which can directly influence prompts/behavior.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)