Oracle Agent Spec Expert

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly defines agent workflows that use web_search and fetch_document/fetch_docs (e.g., the "Multi-Agent System" researcher agent with tools: web_search, fetch_document and the "ResearchPipeline" gather step using [web_search, fetch_docs]), which requires ingesting public web content that can be untrusted/user-generated and could materially influence subsequent agent decisions and tool use.