agentforce-eval-harness
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is entirely descriptive, providing architectural patterns, fixture templates, and instructional guidance (SKILL.md) rather than executable code, installation scripts, or automated tools.
- [SAFE]: No malicious patterns, obfuscation, or insecure data handling were identified.
- The skill references official Salesforce documentation and architectural resources (developer.salesforce.com, architect.salesforce.com) which are well-known and trusted technical services.
- Recommended practices within the documentation include using anonymized data for transcripts and establishing quality gates through established engineering workflows (CI/CD integration).
Audit Metadata