CodeRabbit is using GPT-6.1 Sol as the primary model in its security agent, broadening code review from individual pull requests to risk across complex codebases. A pull request can affect shared libraries, dependencies, and safeguards elsewhere, and Sol helps CodeRabbit connect behavior across files and components to surface potential security issues. CodeRabbit‘s review is independent of the agent that wrote the code and complements established scanners; the system also uses other frontier models and security tooling.

During pull-request review, Sol analyzes changes as developers work. In Deep Scan, CodeRabbit supports broader repository-wide investigation, including dependencies and component interactions. CodeRabbit Secure extends that investigation to linked repositories, such as a shared authentication library, so teams can see how a weakness might affect the wider system.

CodeRabbit reports using Sol to flag security-related issues across thousands of repositories and organizations, feeding findings into the pull-request workflows developers already use. CodeRabbit Secure connects investigation to remediation: for user-selected findings, it can attempt exploit verification in an isolated sandbox without testing production systems; for supported issues, it can draft a pull request with a proposed fix for a person to review and approve.

This work shows how frontier reasoning can support software security by understanding risk beyond an individual change, validating findings, and turning them into proposed fixes. Human reviewers remain responsible for deciding which changes to ship.