rag-retrieval
Warn
Audited by Snyk on Oct 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow uses WebFetch, WebSearch, and RAG retrieval pipelines that ingest arbitrary web pages and external document search results without prior selection, exposing the agent to outsider-authored free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata