omh-decision-prototype

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a platform-specific CLI tool omh (e.g., omh runtime workflow-artifact decision-prototype prepare) to initialize and manage the state of the prototyping workflow. This is a standard integration for the 'Oh-My-Hermes' framework referenced in the skill metadata.
  • [DYNAMIC_EXECUTION]: The core purpose of the skill is to generate and execute 'exact commands' to test technical hypotheses. To mitigate the risk of arbitrary code execution, the skill mandates a 'scratch boundary' (isolated directory or temporary worktree) and requires synthetic fixtures instead of production data.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input, such as 'decision questions' and 'hypotheses'. It implements significant guardrails, including requiring a 'falsifiable hypothesis', budget units (time, tools, files), and explicit verification that the agent is writing within the declared isolation boundary.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:33 PM
Security Audit — agent-trust-hub — omh-decision-prototype