wechat-publisher

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs users to copy raw AppID/AppSecret/access_token values and embed them directly into URLs and curl commands (e.g., access_token=你的TOKEN), which requires including secret values verbatim in output and is an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md section "二、AI Agent 文章创作工作流" (2.1 多模型并行搜索策略) explicitly instructs using web_search to fetch and aggregate public web search results and extract/act on them, so the agent will consume untrusted third‑party web content that can influence its decisions.