deep-research
Warn
Audited by Snyk on Jun 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Deep Research’s REQUIRED workflow includes “Web research — use
WebSearchandWebFetchto gather external information,” which at runtime ingests outsider-authored free text from public web pages into the agent’s LLM context (indirect prompt injection risk).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata