aro-hcp-releases
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local CLI tool (
oncall) via shell scripts (get-releases.shandget-releases.ps1) to fetch pipeline data. The inputs provided by the user (environment, hours, path) are passed as arguments to the CLI. The scripts use secure patterns (Bash arrays and PowerShell splatting) to prevent command injection. - [CREDENTIALS_UNSAFE]: The skill mentions using the
ADO_PATenvironment variable or Azure CLI (az) for authentication to Azure DevOps. It does not hardcode any credentials and follows standard practices for handling access tokens through the environment or existing CLI sessions. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Azure DevOps (pipeline names) and presents it as a markdown table. While this is an external ingestion point, the skill performs no automated or high-risk actions based on the content of these strings, and the data is treated as informative text for the user.
Audit Metadata