qdrant-memory

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill uses a runtime QDRANT_URL (e.g., the external Qdrant Cloud endpoint https://cloud.qdrant.io) to fetch stored memory chunks that are then injected into prompts/contexts—so remote content from that URL directly controls agent prompts and is a required dependency.