azure-arg-external-evaluation-policy-author
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
az graph querycommand to validate Azure Resource Graph queries during an iterative co-design workflow. This is a core intended functionality and is restricted to read-only operations by the skill's internal rules, which explicitly prohibit modifying, creating, or deleting resources in the user's subscription. - [INDIRECT_PROMPT_INJECTION]: The skill processes structured JSON output from tool executions to assist the user. To mitigate risks associated with processing external data, the skill instructions mandate the use of generic placeholders (e.g.,
<subId>,<rgName>) to replace sensitive environment-specific information in all generated policy definitions, HTTP test flows, and documentation.
Audit Metadata