news-summarizer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests articles from Google News and other open web sources using its search_web step and then reads/summarizes those public article contents and returns original links, which exposes the agent to arbitrary third‑party web content that could carry malicious or instruction-like text.