sf-ai-agentforce

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate technical documentation and metadata examples for Salesforce Agentforce development, including GenAiFunction, GenAiPlugin, and PromptTemplate structures.
  • [SAFE]: No malicious obfuscation, hardcoded credentials, or unauthorized network operations were found in any of the files.
  • [SAFE]: The skill correctly delegates specialized development tasks (Apex, Flow, Deployment) to other dedicated skills, following a modular and secure orchestration pattern.
  • [SAFE]: While the skill documents agents that ingest untrusted user input via PromptTemplates, the examples provided include boundary markers (e.g., "--- KNOWLEDGE CONTEXT ---") and restrictive system instructions, which align with recommended safety practices for LLM integration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 03:25 PM