skill-builder

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

• Third-party content exposure detected (high risk: 0.80). This SKILL.md explicitly instructs the agent to use public web search and URL-reading tools (searxng_searxng_web_search, searxng_web_url_read) in the "Research & Validation" and "Workflow Plan" sections to fetch and read third‑party web content, which the agent is expected to interpret to drive implementation decisions.