azure-ai-projects-py
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill documents how to build agents that ingest untrusted data from external sources, constituting a potential surface for indirect prompt injection.
- Ingestion points: Documentation in 'SKILL.md' and 'references/datasets-indexes.md' describes uploading files and datasets, while 'scripts/run_batch_evaluation.py' processes JSONL data files.
- Boundary markers: Examples do not explicitly demonstrate the use of delimiters or instructions to prevent the model from obeying commands hidden within processed data.
- Capability inventory: Agents can be configured with powerful tools including 'CodeInterpreterTool' for Python execution and 'FunctionTool' for running custom logic.
- Sanitization: No explicit content sanitization or validation steps are presented in the provided implementation examples.
Audit Metadata