omh-physical-device-readiness
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a safety-gated workflow specifically designed to prevent unauthorized or unsafe physical device interactions.
- [SAFE]: The instructions clearly distinguish between 'prepared guidance' and 'observed evidence', preventing the agent from falsely claiming successful execution of physical tasks.
- [SAFE]: No instances of prompt injection, data exfiltration, or obfuscation were found. The use of the 'omh' CLI for runtime tracking is a local operational tool consistent with the skill's purpose.
- [SAFE]: The inclusion of an 'approvals.deny' glob list recommendation is a defensive security measure to block dangerous terminal commands from autonomous execution.
Audit Metadata