omc-plan

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill.
  • [COMMAND_EXECUTION]: The skill invokes platform-specific sub-agents (planner, architect, critic, analyst) and transitions to execution skills (ralph, team). These are internal platform capabilities used as intended for collaborative planning and subsequent task execution.
  • [EXTERNAL_DOWNLOADS]: The skill supports an optional integration with external model providers (OpenAI Codex) via the platform's CLI tool ('omc ask codex') when explicitly requested by the user via command-line flags.
  • [DATA_EXFILTRATION]: No patterns of unauthorized data collection or exfiltration were detected. Codebase exploration is performed using an internal 'explore' agent to inform the planning process.
  • [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters or override system-level constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 01:10 AM
Security Audit — agent-trust-hub — omc-plan