skills/opengovsg/formsg-ai/grilling/Gen Agent Trust Hub

grilling

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructional guidance for a 'grilling' persona, using a design tree to explore user ideas. It does not contain prompt injections, hardcoded credentials, or suspicious network operations. The request for the agent to use sub-agents to gather facts from the environment is a functional requirement for its stated purpose and relies on the agent's existing tool capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 01:23 PM