CodeRabbit taps GPT-6.1 Sol to scan codebases for security risks

CodeRabbit's setup reflects a specific gap in AI-assisted coding: a single change can ripple into shared libraries, dependencies and safeguards elsewhere in an application, which a review limited to the diff may miss. GPT-6.1 Sol is used to connect behavior across files and components and surface potential security issues, and the review is kept independent of the agent that wrote the code.

The scope widens step by step. During pull-request review, the model analyzes changes as developers work; Deep Scan supports broader investigation across repositories, including dependencies and how components interact; and CodeRabbit Secure extends that to linked repositories such as a shared authentication library, so teams can see how a weakness could affect the wider system. CodeRabbit reports using GPT-6.1 Sol to flag security-related issues across thousands of repositories and organizations, with findings feeding into existing pull-request workflows.

The remediation side is deliberately gated. For user-selected findings, CodeRabbit Secure can attempt exploit verification in an isolated sandbox without testing production systems, and for supported issues it can draft a pull request with a proposed fix. Human reviewers remain responsible for deciding which changes to ship—consistent with the stated aim of keeping people in control as AI speeds up software development.