deep-research
Warn
Audited by Snyk on Aug 13, 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). [Deep Research] ingests outsider-authored free text via its runtime “Search Strategy” and “Extraction” steps that perform targeted web searches (including public sites like GitHub) and then scrape the resulting source pages into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata