orchestrate

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This orchestrator intentionally runs external agent CLIs in "full‑auto" (bypassing their safety prompts), sources user-editable profile/meta files, and auto‑dismisses trust dialogs — together these design choices create high-risk vectors for remote code execution, supply‑chain/backdoor insertion, and data exfiltration by an agent process.