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
Risk Level
SAFE
Analyzed
Jun 16, 2026, 12:58 AM
Security Audit — agent-trust-hub — agentforce-eval-harness