plan-alm
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill executes local helper scripts and official Microsoft CLI tools (Power Platform CLI
pacand Azure CLIaz) to perform environment discovery. It also utilizes native system commands such asStart-Process,open, orxdg-opento display the generated HTML plan in the user's browser, which is a standard operational pattern for this type of tool. - Indirect Prompt Injection: The skill processes external data retrieved from Dataverse API endpoints, including site settings and environment names. To manage potential risks from untrusted data, the rendering logic applies HTML escaping to sanitize these values before they are included in the generated HTML report.
- Credential Management: The skill obtains temporary authenticated tokens for Dataverse and Power Platform APIs using official CLI tools. These tokens are used locally for discovery tasks and are not stored permanently or transmitted to unauthorized external services.
- Integrity and Validation: The skill includes a dedicated validation script that monitors the consistency of the generated deployment plan. It verifies that the plan status and the recorded audit trail (approver information) are correctly synchronized, ensuring the reliability of the generated documentation.
Audit Metadata