docs

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). High-risk: the skill instructs automated agents and external LLM calls that read and modify repository source/docs (including CHANGELOG, backend/, src/, and potentially .env/config files) and to auto-apply/commit changes and deploy — creating clear vectors for unauthorized data exfiltration and supply-chain/backdoor injection.