agentforce-development

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides educational content and templates for Salesforce development. All instructions and scripts align with standard developer workflows for the Salesforce platform.
  • [PROMPT_INJECTION]: The skill includes instructions for creating guardrail topics (e.g., off_topic, ambiguous_question) designed to prevent prompt injection and unauthorized system information disclosure. These are properly implemented security features.
  • [DATA_EXFILTRATION]: No unauthorized data transmission or exfiltration patterns were detected. The skill uses standard Salesforce CLI commands and internal Salesforce protocols (apex://, flow://) for data operations.
  • [CREDENTIALS_UNSAFE]: Usernames appearing in example configuration files are placeholders for required configuration fields and do not expose sensitive secrets or credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 08:55 PM