guardrails-safety
Warn
Audited by Snyk on Jul 8, 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 required workflow explicitly ingests “Retrieval Context” (retrieved documents/chunks) into the prompt context for the retrieval guardrail (RAG), and those retrieved chunks are outsider-authored free text when they come from external/vector-store sources not authored by the operating user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata