qdrant-patterns
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The documented RAG workflow involves fetching external content, which creates a surface for indirect prompt injection. This is a standard risk for memory-retrieval skills and no malicious patterns are present.\n
- Ingestion points: External data fetched via tools like WebFetch or Read (SKILL.md)\n
- Boundary markers: Absent in the provided markdown examples (SKILL.md)\n
- Capability inventory: qdrant-store, qdrant-find (SKILL.md)\n
- Sanitization: Absent in the provided markdown examples (SKILL.md)
Audit Metadata