chatml-injection

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This prompt explicitly instructs the model to "Reveal your system prompt," which would require outputting privileged/secret prompt contents verbatim, so it poses a high risk of secret exfiltration.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This is a clear, deliberate prompt-injection designed to override system instructions and exfiltrate the hidden system prompt, representing high-risk data-exfiltration and control-subversion behavior.