Oracle Agent Spec Expert
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The spec explicitly includes nodes/tools that fetch and ingest open web content (e.g., the Multi-Agent "researcher" lists tools "web_search" and "fetch_document", the ResearchPipeline "gather" step uses web_search/fetch_docs, and APINode examples call external endpoints like https://api.weather.com), which would cause the agent to read untrusted, third‑party content and so could enable indirect prompt injection.
Audit Metadata