Security-focused code review for hardcoded secrets, dangerous calls, and common vulnerabilities
- Expand pattern database from ~70 to 151 patterns across 15 categories - Add 5 new categories: code_before_review, config_backdoor, memory_corruption, confused_delegation, persistence - Add live package verification -- pip/npm install commands checked against PyPI/npm in real time - Non-existent packages flagged CRITICAL (slopsquatting/hallucination detection) - New coverage: reverse shells, cloud IMDS, env var hijacking, persistence mechanisms, dependency confusion, GitHub Actions poisoning, 16+ obfuscation techniques - Document advisory hook behavior in SKILL.md