salesforce

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill explicitly mandates that the agent must display planned changes and obtain user approval before executing any data-modifying commands (create, update, or delete).
  • [COMMAND_EXECUTION]: The instructions utilize the legitimate Salesforce CLI (sf) for database queries and record management, following standard industry practices for CRM integration.
  • [DATA_EXFILTRATION]: No malicious data exfiltration patterns were detected. The skill includes specific warnings for the agent to avoid including sensitive information like access tokens in its output.
  • [PROMPT_INJECTION]: The skill instructions do not contain any patterns intended to bypass AI safety filters or override core agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 05:17 AM
Security Audit — agent-trust-hub — salesforce