agents-v2-py
Pass
Audited by Gen Agent Trust Hub on Feb 14, 2026
Risk Level: LOWEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill references the installation of 'azure-ai-projects' and 'azure-identity' via pip. These are official packages maintained by the Microsoft/Azure organization, which is a trusted source per [TRUST-SCOPE-RULE].
- [CREDENTIALS_UNSAFE] (SAFE): No hardcoded API keys, secrets, or credentials were found. The skill correctly demonstrates using 'DefaultAzureCredential' and environment variables for endpoint configuration.
- [COMMAND_EXECUTION] (SAFE): The skill facilitates the deployment of containerized agents that can execute code (via 'code_interpreter'), but the skill's own code does not perform arbitrary or unsafe command execution on the host system.
- [PROMPT_INJECTION] (SAFE): No malicious instructions, bypass attempts, or safety filter overrides were detected in the skill content or metadata.
Audit Metadata