service-itsm-agentic-setup-incident-sla-configure
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill performs administrative configuration changes on the target Salesforce environment using the platform-integrated
headless-360MCP tool. This includes creating and activating SLA policies, milestones, and entitlements. These actions are governed by explicit permission checks (UserPermissions.CustomizeApplication) and involve logical gating based on feature enablement status. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Salesforce environment, such as record picklist values and discovery feature statuses. This ingestion surface is used to drive automated setup tasks. The risk is mitigated by the skill's requirement for human confirmation of the plan before execution and the use of structured JSON templates for tool interactions.
- [DATA_EXPOSURE]: The skill implements a strict 'Output Contract' that prohibits the display of raw Salesforce record IDs in user-facing text to prevent accidental data exposure or fingerprinting. It ensures that only descriptive names and verified attributes are shared with the user.
Audit Metadata