tech-hub

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

• Third-party content exposure detected (high risk: 1.00). The skill's required execution flow ("执行流程" → "第一步：全球扫货 / AI专栏（必搜，优先级最高）") explicitly instructs the agent to fetch and ingest open public sources (The Information, TechCrunch, Bloomberg, official blogs/Twitter, 财联社, 36氪, etc.) and use those items to drive A-share mapping and investment actions, so untrusted third‑party content can be read and materially influence behavior.