qdrant-fastapi-integration

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses official and well-known libraries including qdrant-client, openai, and python-dotenv.\n- [PROMPT_INJECTION]: The script scripts/upsert_vectors.py ingests untrusted text from local files for storage in a vector database, creating a surface for indirect prompt injection.\n
  • Ingestion points: The script reads document content from a user-specified directory.\n
  • Boundary markers: No delimiters or instructions are used to separate user data from system instructions in the stored payload.\n
  • Capability inventory: The skill performs file reads and network requests to external API services (Qdrant and OpenAI).\n
  • Sanitization: No sanitization is performed on the ingested text to prevent embedded instructions from being stored.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 03:39 PM
Security Audit — agent-trust-hub — qdrant-fastapi-integration