CodeRabbit is using OpenAI’s GPT-6.1 Sol in its security agent to investigate code risks across repositories and help developers review proposed fixes.
OpenAI said on October 26, 2026, that CodeRabbit is using GPT-6.1 Sol as the primary model in its security agent. The system is intended to help developers spot potential vulnerabilities that may involve multiple files, components, or repositories—not just the code in an individual change.
The model assists with pull-request reviews as developers work and with broader investigations through CodeRabbit’s Deep Scan. CodeRabbit Secure can extend analysis to linked repositories, which can help teams examine how a weakness in a shared component, such as an authentication library, might affect other systems. OpenAI said CodeRabbit reports using Sol to flag security-related issues across thousands of repositories and organizations.
The workflow also connects findings to possible remediation. For findings users select, CodeRabbit Secure can attempt to verify an exploit in an isolated sandbox rather than test production systems. For supported issues, it can draft a pull request proposing a fix; a human reviewer remains responsible for deciding whether to approve it.
OpenAI described Sol’s role as complementary to existing scanners and CodeRabbit’s other security tools. The agent that reviews code is also independent of the agent that wrote it, according to the company. That separation is intended to provide another review path, while the broader repository analysis can surface relationships that a single-change review might not capture.
The announcement describes assistance with investigation, validation, and proposed fixes—not autonomous approval or deployment. Developers retain control over which findings to act on and which changes to ship.