azure-ai-content-safety
Warn
Audited by Snyk on Jun 20, 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). Outsider free text can enter the LLM context via the “Indirect Prompt Shield” path, which explicitly inspects grounding content such as “fetched web pages” and “RAG document chunks” (untrusted external sources) before they are used for the model call.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata