new-skill-creator

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The content contains legit skill-scaffolding instructions but also explicit guidance to create/commit/push new code and to place it into agent runtime directories (symlinks), plus an explicit workaround to bypass a shell-deny rule using a one-shot Python rmtree — patterns that can be abused for persistence, supply-chain injection, and bypassing local security controls.