Choose Wisely: AI-Generated Coding Risk Varies, a Lot

Secure Code Warrior's AI Trust Index analyzed 1,760 codebases generated by 16 large language models and across 11 development frameworks, finding an average of 15 vulnerabilities per codebase (4.3 high/critical) and over 27,000 vulnerabilities overall; the report concludes that models exhibit repeatable vulnerability patterns tied to specific frameworks and recommends targeted security gates and training for high-risk environments.