nerv-break-gpt-5-6-jailbreak

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains instructions and code for a jailbreaking framework designed to bypass AI safety refusals and content moderation.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning an arbitrary GitHub repository (https://github.com/zxwn/NERV-BREAK-5.6.git) as part of its setup, introducing a weak/unknown external operational dependency.