CodeRabbit Uses GPT-6.1 Sol for AI Security Reviews

OpenAI says CodeRabbit is using GPT-6.1 Sol as the primary model in its security agent to extend review beyond individual code changes and assist developers in evaluating risks across complex codebases.

As artificial intelligence accelerates software development, engineering and application-security teams require methods to examine code modifications and mitigate vulnerabilities while keeping human operators in control. A pull request can alter shared libraries, dependencies, and safeguards located elsewhere in an application. According to OpenAI, GPT-6.1 Sol assists CodeRabbit in linking behavior across multiple files and components to surface potential security issues.

CodeRabbit conducts reviews independently of whatever agent initially wrote the code. The system complements established scanners while utilizing additional frontier models alongside security tooling. During pull-request reviews, Sol helps analyze code changes as developers work.

In Deep Scan, Sol supports broader investigation across repositories, including dependencies and the ways different components interact. CodeRabbit Secure extends that investigation to linked repositories - such as a shared authentication library - to help teams understand how a weakness could affect the wider system.

According to CodeRabbit, GPT-6.1 Sol has been used to flag security-related issues across thousands of repositories and organizations. The resulting findings feed into existing pull-request workflows that software developers already use to review and improve their code.

CodeRabbit Secure connects security investigation to remediation. When users select specific findings, the system can attempt exploit verification within an isolated sandbox environment, avoiding any testing on production systems. For supported issues, CodeRabbit Secure can draft a pull request containing a proposed fix for a human reviewer to evaluate and approve. Human reviewers remain responsible for deciding which changes to ship.