qdrant
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill exposes the agent to untrusted, user-provided content because it includes endpoints and flows that ingest arbitrary documents into Qdrant (e.g., POST /api/rag/ingest and POST /api/search/document) which are then retrieved by the LangChain4j/Qdrant content retriever and read by the assistant for RAG.
Audit Metadata