newsnow

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly fetches and returns content from open public sources (e.g., Weibo, Tieba, Bilibili, Hacker News, Product Hunt, Zhihu) via commands like newsnow <source> --json and instructs consuming/processing those results, which exposes the agent to untrusted user-generated third‑party content that could contain malicious instructions.