CodeRabbit says the system reviews pull-request changes alongside shared libraries, dependencies, and safeguards elsewhere in a codebase.
In its Deep Scan mode, the service investigates risks across repositories and component interactions. CodeRabbit Secure can extend that investigation to linked repositories, such as a shared authentication library. For user-selected findings, it can attempt exploit verification in an isolated sandbox rather than against production systems. For supported issues, it can draft a pull request proposing a fix for human review and approval.
CodeRabbit says it uses GPT-6.1 Sol to flag security-related issues across thousands of repositories and organizations, while also using other frontier models and security tooling. The source does not provide detection or false-positive rates, comparative benchmarks, pricing, the number of customers, or evidence that proposed fixes are accepted or shipped.