az-tool
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill acts as a bridge for the az-tool CLI, which is part of the @blogic-cz/agent-tools suite provided by the same author.
- [COMMAND_EXECUTION]: The instructions direct the agent to run various bun az-tool commands. These commands are restricted to informational Azure DevOps tasks such as listing pipelines, showing build summaries, and retrieving log content.
- [DATA_EXPOSURE]: The tool accesses sensitive pipeline data and build logs. However, it leverages the user's existing az login session, ensuring that access is governed by the user's own permissions and security context.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading log content from external builds. While this represents a potential surface for indirect prompt injection (where instructions hidden in logs might influence the agent), it is a necessary feature of a log-reading tool and is documented here as an inherent risk factor rather than a malicious implementation.
Audit Metadata