newsapi

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md instructs use of NewsAPI actions (e.g., "Search Everything" which searches millions of articles from over 150,000 news sources and blogs) and shows running actions whose output the agent consumes, so it ingests untrusted public web content that could contain instructional or manipulative text affecting decisions.