deep-researcher
Warn
Audited by Snyk on Mar 7, 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 SKILL.md workflow (Step 2 "Conduct Initial Exploratory Research", Step 3 "Deep Dive into Key Areas", and the "Prefer primary sources" guidance) explicitly instructs the agent to search for, retrieve, and ingest information from external/public sources, which can include untrusted web or user-generated content and therefore could enable indirect prompt injection.
Audit Metadata