deep-research
Warn
Audited by Snyk on Nov 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required RETRIEVE phase has the agent run WebSearch and Exa searches and WebFetch selected pages, so it ingests arbitrary outsider-authored web content, but only after the agent actively searches or fetches it, so an attacker can publish poison but cannot force delivery.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata