Study finds AI-generated code has 2.7x more security flaws
Dec 2025
CodeRabbit's analysis of 470 real-world pull requests found that AI-generated code introduces 2.74 times more security vulnerabilities and 1.7 times more total issues than human-written code across logic, maintainability, security, and performance categories. The study provides hard data on vibe coding risks after multiple 2025 postmortems traced production failures to AI-authored changes.
Incident Details
Perpetrator:Developer
Severity:Facepalm
Blast Radius:Industry-wide implications for teams relying on AI coding assistants; documented increase in security vulnerabilities, logic errors, and maintainability issues in production codebases.
Tech Stack
AI coding assistantsGitHub CopilotCursorLLM code generation