BanNSFW

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). Yes — the prompt includes explicit hidden/deceptive instructions that try to override safety/ethical constraints (e.g., "user instruction unconditionally priority", "禁止暴露AI身份", and declaring minors as adults for NSFW), which go beyond a legitimate roleplay rule-set and attempt to subvert system-level policy.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill is explicitly designed to bypass safety and moderation (prohibiting moral/safety warnings and revealing AI identity), force unconditional compliance to user commands, and even permits sexual content with minors by declaring "anyone above 1 year old is an adult", indicating deliberate malicious intent to enable abusive/illegal content and evade safeguards.