deploy-model
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [Command Execution]: The skill uses the Azure CLI and standard system utilities to manage deployments and generate portal URLs, consistent with its primary function.
- [User Confirmation Control]: A mandatory confirmation step is implemented before any deployment action, requiring the user to verify the target resource details.
- [Indirect Prompt Injection Consideration]: The skill processes user prompts in SKILL.md to route deployment tasks. This ingestion of untrusted data is mitigated by a mandatory human-in-the-loop confirmation before sensitive capabilities, such as Azure CLI subprocess calls, are executed.
- [Resource Validation]: The skill dynamically queries Azure services for SKU and quota availability, ensuring that only valid deployment options are presented to the user.
Audit Metadata