azure-monitor-query-java
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the
azure-monitor-querylibrary (version 1.5.9) from the official Maven Central repository. This package is maintained by Microsoft, a trusted organization. - [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface where the agent processes data from Azure Monitor logs.
- Ingestion points:
LogsQueryResultdata ingested via thequeryWorkspaceandqueryResourcemethods inSKILL.md. - Boundary markers: The provided code snippets do not include explicit delimiters or warnings to ignore instructions embedded within the log data.
- Capability inventory: The skill demonstrates read-only access to monitoring data and basic output via standard Java logging/printing. It does not include scripts for file system modification, arbitrary command execution, or outbound network calls to untrusted domains.
- Sanitization: No explicit sanitization or filtering of the retrieved log content is shown in the examples.
Audit Metadata