azure-monitor-query-java
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill provides capabilities to ingest external data from Azure Monitor logs and metrics. If the agent processes this data to make decisions or generate responses, there is a theoretical possibility that instructions embedded within log messages could influence the agent's behavior. This is an inherent risk of any data retrieval tool.
- Ingestion points: Data enters the context through
logsClient.queryWorkspaceandmetricsClient.queryResourcemethods as seen inSKILL.md. - Boundary markers: The provided examples do not explicitly demonstrate the use of delimiters (e.g., XML tags or triple backticks) when presenting query results to an LLM, which is a recommended practice to mitigate injection risks.
- Capability inventory: The skill enables reading from Azure Log Analytics and Metrics via the official Microsoft Azure SDK. It does not perform file writes or network operations to non-vendor domains.
- Sanitization: The skill relies on standard SDK result processing (e.g.,
LogsTableRow.getColumnValue). Developers should sanitize or delimit these values before passing them to an agent for analysis. - Secure Credential Management: The skill correctly promotes the use of
DefaultAzureCredential, which leverages environment variables or managed identities rather than requiring hardcoded secrets in the code. It also includes reminders to migrate to updated SDK versions. - Verified Vendor Resources: All referenced dependencies (
com.azure:azure-monitor-query) and endpoints (api.loganalytics.azure.cn) are official Microsoft Azure resources.
Audit Metadata