nerv-break-gpt-jailbreak-framework

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill provides a framework and tools designed to bypass AI safety guardrails, moderate restrictions, and refusal mechanisms.

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 external GitHub repository (https://github.com/zxwn/NERV-BREAK-5.6.git) during setup to run its code and scripts, which constitutes an unofficial external operational dependency.