ai-security-knowledge-base

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The document includes explicit, intentionally malicious capabilities — e.g., malware mutation for AV evasion, automated exploit generation, real-time deepfake face‑swapping, and voice‑cloning with a phishing example — which clearly facilitate wrongdoing beyond benign research.