service-itsm-agentic-setup-cmdb-bundle-deploy
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Salesforce Connect API responses (bundle lists and details) to resolve versions for installation. While this represents an external data ingestion surface, the risk is mitigated by the fact that the data originates from a trusted Salesforce backend. Furthermore, the skill enforces a mandatory user confirmation step in Step 3, ensuring the user reviews the specific bundle and version before the installation POST request is dispatched.
- [COMMAND_EXECUTION]: The skill utilizes specialized MCP tools (
mcp__headless-360__dispatch) to execute HTTP requests against Salesforce API endpoints. These operations are well-scoped to the skill's primary function of bundle management. The implementation relies on the platform's OAuth session for authentication, preventing the skill from directly handling or exposing sensitive credentials. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses Salesforce-specific metadata and configuration endpoints. All network operations are directed at official Salesforce Connect API paths (
/services/data/v67.0/connect/...). No sensitive local files are accessed, and no data is transmitted to unauthorized or unknown external domains.
Audit Metadata