Oracle Agent Spec Expert

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly defines agents that use tools like "web_search", "fetch_document"/"fetch_docs" (Multi-Agent System researcher and ResearchPipeline gather steps) and APINode endpoints (e.g., https://api.weather.com/...) which require fetching public, user-generated or third-party web content that the agent ingests and acts on, enabling indirect prompt injection.