azure-resource-health-diagnose
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Azure logs and telemetry to inform its diagnostic analysis and remediation plan.
- Ingestion points: Data enters the agent context via
azmcp-monitor-log-queryand KQL queries as described in Step 4. - Boundary markers: No explicit delimiters are provided to the agent to distinguish between its instructions and potentially malicious content within log entries.
- Capability inventory: The skill uses Azure CLI (
az) and multipleazmcptools to interact with and manage cloud infrastructure across Steps 2, 4, and 7. - Sanitization: The skill does not explicitly describe sanitization for log content; however, the risk is mitigated by the workflow design, which requires user approval in Step 7 before implementing any recommended fixes.
- [COMMAND_EXECUTION]: The skill is designed to execute Azure CLI commands and utilize MCP tools to manage cloud resources. This behavior is necessary for its core functionality of resource discovery and health assessment and is limited to the user's authenticated Azure environment.
Audit Metadata