agent-creator

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill intentionally executes untrusted, model-authored Python code in child processes (exec of compiled snippets, a JSON stdin/stdout runner that always exits 0) and explicitly notes the lack of OS-level sandboxing, which enables remote code execution and potential data exfiltration if abused.