automation-flow-generate

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a structured workflow for using the execute_metadata_action tool to generate Salesforce Flow XML. The instructions are focused on technical compliance with the Salesforce metadata API.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the execute_metadata_action MCP tool. This is a legitimate integration for Salesforce development. The skill includes constraints to ensure the agent follows a strict sequential pipeline, which is a standard procedure for complex metadata generation.
  • [PROMPT_INJECTION]: The skill uses strong instructional language such as 'MANDATORY' and 'STRICT CONSTRAINTS'. These are intended to ensure the AI agent adheres to the technical requirements of the Salesforce pipeline rather than attempting to bypass safety filters or ignore system instructions.
  • [DATA_EXFILTRATION]: No evidence of hardcoded credentials, unauthorized network requests, or sensitive data exposure was found. The skill operates within the context of an established Salesforce development environment ('sfdx project').
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 07:43 AM
Security Audit — agent-trust-hub — automation-flow-generate