service-itsm-agentic-setup-incident-management
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a coordinator (orchestrator) and only uses standard tools like
ReadandAskUserQuestion. It does not perform any sensitive operations, network requests, or direct file system writes. It delegates specific configuration tasks to child skills likeservice-itsm-agentic-setup-incident-sla-configure, ensuring a separation of concerns. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user input via chat history and
AskUserQuestion. However, the capabilities are restricted to delegation and progress tracking. It includes explicit instructions to verify user intent and state before proceeding, which serves as a basic boundary marker against accidental execution. Severity for this category is inherently low as it only poses a surface for potential instruction confusion in the selection menu.
Audit Metadata