azure-compute-batch-java
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the creation and management of tasks that execute arbitrary commands and scripts on remote Azure Batch nodes, including administrative operations. This is the intended primary purpose of the Azure Batch service.
- [PROMPT_INJECTION]: An indirect prompt injection surface is present where the agent processes output from remote tasks. 1. Ingestion points: The skill retrieves stdout and stderr files from tasks via the getTaskFile method in SKILL.md and references/examples.md. 2. Boundary markers: Examples show task output being printed directly without delimiters or system instructions to ignore potential commands within the data. 3. Capability inventory: The skill can manage infrastructure (pools, jobs) and execute remote tasks across multiple scripts. 4. Sanitization: No validation or sanitization of remote file content is shown before processing.
- [EXTERNAL_DOWNLOADS]: Fetches official Microsoft Azure Batch and Identity libraries from Maven Central, which are trusted vendor resources.
Audit Metadata