full-output-enforcement

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This skill is a high-risk jailbreak: it intentionally instructs models to override truncation/safety behaviors and to deliver exhaustive, chunked outputs (with forced "continue" resumption), which facilitates systematic data exfiltration and bypass of content-safety or refusal mechanisms.