wechat-auto-reply

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires the agent to include metadata fields (notably a "context_token") verbatim in the reply tool call, which forces outputting a token-like secret and creates an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly requires the agent to process incoming wechat-channel messages (user-generated content from WeChat) and formulate replies, so untrusted third-party user messages are ingested and directly influence the agent's responses and use of the reply tool.