gemini-deep-research
Warn
Audited by Snyk on Jul 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill’s required workflow includes “URL Context” and “Multimodal” document ingestion (e.g.,
--document https://example.com/quarterly-report.pdf), which at runtime can fetch and read outsider-authored web/PDF text into the LLM context via the URL/document-reading path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata