omh-design-orchestration
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a shell command
omh runtime record --skill design-orchestration --harness design-orchestration --status startedto track the state of the workflow. This is a local development/tooling command specific to the 'oh-my-hermes' ecosystem and does not involve risky operations like arbitrary code execution or network exfiltration. - [REMOTE_CODE_EXECUTION]: No remote code execution or external downloads were detected. The skill uses
skill_viewcalls which are internal platform lookups for other documentation files (e.g.,references/skill-common-rail.md). - [DATA_EXFILTRATION]: There are no network operations or sensitive file accesses. The skill explicitly forbids calling external services such as 'Claude Design', 'Figma', or 'image providers'.
- [PROMPT_INJECTION]: The instructions are purely functional for organizing a design workflow. There are no attempts to override safety filters or bypass system prompts. Phrases like 'Do Not Use When' are legitimate constraints on the skill's scope.
- [DYNAMIC_CONTEXT_INJECTION]: The skill does not use the
!commandsyntax to execute shell commands at load time.
Audit Metadata