NYC

FastAPI Customer Support Tech Enablement

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: CRITICALPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill's primary function is to process untrusted data (support tickets and chat) which creates a surface for indirect prompt injection.
  • Ingestion points: Support ticket CRUD API and WebSocket chat support described in EXAMPLES.md.
  • Boundary markers: Documentation mentions Pydantic validation for incoming data, though specific prompt isolation techniques are not detailed in the summary.
  • Capability inventory: The skill interacts with databases, handles file uploads, and sends email notifications.
  • Sanitization: Implements Pydantic v2 for input schema validation.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill requires standard, well-maintained Python packages (fastapi, uvicorn, sqlalchemy, asyncpg, pydantic, python-jose, passlib) from official registries.
  • [COMMAND_EXECUTION] (SAFE): Documentation includes instructions for starting the service via 'uvicorn', which is the standard procedure for ASGI applications.
  • [MALICIOUS_URL_DETECTION] (SAFE): The automated scan alert for 'logger.info' is identified as a false positive, likely misinterpreting a standard Python logging statement as a malicious .info domain.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 06:20 PM