researching-azure-ai-sdk
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references multiple official GitHub repositories for Azure and Microsoft Foundry. These are trusted sources, and the references are intended for informational lookup only.
- [COMMAND_EXECUTION]: The skill contains PowerShell snippets intended for local developer use to inspect SDK types via reflection. These are not executed automatically by the agent.
- [PROMPT_INJECTION]: The research delegation pattern creates a surface for indirect prompt injection by ingesting data from external repositories into the subagent context. Mitigation is present through explicit instructions to the subagent to avoid code generation, use pseudocode only, and adhere to a 20-line output limit. Capabilities across the skill are restricted to documentation and sample lookup with no automated file-write or network-send operations beyond the research fetching.
Audit Metadata