agno

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

• Third-party content exposure detected (high risk: 0.90). The skill's documentation and examples (e.g., SKILL.md Quick Reference and references/examples.md) explicitly show agents using web-facing tools like DuckDuckGoTools, HackerNewsTools, GoogleSearchTools, Newspaper4k, and Crawl4ai to fetch and scrape public websites (e.g., web search results, HN posts, news articles) and then act on that content (e.g., research and blog_post_generator workflows), which clearly exposes the agent to untrusted, user-generated third‑party content that can influence tool use and subsequent actions.