OpenAI said Monday that CodeRabbit is using GPT-6.1 Sol as the primary model in its security agent, which is meant to investigate security risks across complex codebases rather than only individual code changes¹.

The company said a pull request can affect shared libraries, dependencies and safeguards elsewhere in an application, and that Sol helps CodeRabbit connect behavior across files and components¹. OpenAI said CodeRabbit’s review is independent of the agent that wrote the code and complements established scanners, and that the system also uses other frontier models and security tooling¹.

During pull-request review, Sol helps analyze changes as developers work, OpenAI said¹. In a mode called Deep Scan, it supports broader investigation across repositories, including dependencies and how components interact¹. CodeRabbit Secure extends that investigation to linked repositories, such as a shared authentication library, according to the post¹.

CodeRabbit reports using GPT-6.1 Sol to flag security-related issues across thousands of repositories and organizations, OpenAI said, with findings feeding into existing pull-request workflows¹.

For user-selected findings, CodeRabbit Secure can attempt exploit verification in an isolated sandbox without testing production systems, OpenAI said¹. For supported issues, it can draft a pull request with a proposed fix for a person to review and approve¹.

OpenAI said human reviewers remain responsible for deciding which changes to ship¹. Independent reporting on CodeRabbit’s results, customer uptake or how often proposed fixes are accepted was not included in the company post¹.

Sources

1. OpenAIGPT-6.1 Sol helps CodeRabbit strengthen security across complex codebases9:45 AM

Read the original at OpenAI ↗