sf-vlocity-build-deploy
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes DataPack JSON files and CLI command outputs, creating a surface for indirect prompt injection.\n
- Ingestion points: DataPack JSON files (e.g., Business-Internet-Plus_DataPack.json) and Vlocity job YAML files are read and processed by the skill, along with output from vlocity and sf commands.\n
- Boundary markers: No specific boundary markers or instructions to ignore instructions within processed data are present in the skill instructions.\n
- Capability inventory: The skill leverages CLI tools (vlocity, sf) with capabilities for file system access and network operations related to Salesforce org deployments.\n
- Sanitization: Content from external files and command outputs is not sanitized or validated before being incorporated into the agent's context.
Audit Metadata