wechat-writer-kit

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 1 explicitly performs web_search queries (account keywords + "今日热搜") to fetch open-web results and social/trending content which the agent reads and uses to generate and choose article topics, exposing it to untrusted third‑party user-generated/public content that could carry malicious instructions.