sf-ai-agentforce-conversationdesign
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and templates for AI agent design, including persona development, topic architecture, and instruction writing. These are purely informational resources.
- [SAFE]: Included Python script
instruction-quality-validator.pyis a local utility for linting instruction text. It uses standard libraries for regex matching and does not perform any sensitive operations such as network requests or file modifications. - [SAFE]: The use of a lifecycle hook in
.claude/hooks.yamlto execute the local validation script is a benign developer productivity feature. - [SAFE]: References to external documentation from Google, IBM, and Salesforce are for educational purposes and point to well-known, trusted domains.
Audit Metadata