Autofix provides you with targeted recommendations to help you fix code scanning alerts so you can avoid introducing new security vulnerabilities. The potential fixes are generated automatically by large language models (LLMs) using data from the codebase and from code scanning analysis.
How autofix works
Autofix translates the description and location of a code scanning alert into code changes that may fix it. It interfaces with the large language model GPT-5.3-Codex from OpenAI, which has sufficient generative capabilities to produce both suggested fixes in code and explanatory text for those fixes.
There are two ways to get a fix for an alert: agentic autofix and Copilot の自動修正. If Copilot クラウドエージェント is available in a repository, assigning an alert uses agentic autofix instead of Copilot の自動修正.
Agentic autofix
メモ
This feature is currently in public preview and is subject to change.
Assign a code scanning alert to Copilot to have it resolve the alert for you. Assigning an alert starts an agent session: Copilot クラウドエージェント calls tools to explore your codebase beyond the affected file, generates a fix, validates it (for example, by re-running CodeQL), and iterates until it opens a pull request with the changes. See コード スキャン アラートを解決する.
Keep the following in mind:
- Agentic autofix requires Copilot クラウドエージェント and Copilot の自動修正 to be available in the repository. If Copilot クラウドエージェント isn't available, assigning an alert falls back to Copilot の自動修正 instead.
- Each agentic autofix session is billed as a Copilot クラウドエージェント session and consumes AI credits. See クラウド エージェントGitHub Copilotについて.
- Copilot follows any custom instructions configured for the repository or organization when it generates a fix.
- Agentic autofix works on a best-effort basis. Copilot validates fixes by re-running CodeQL using the code-scanning query suite, so it can't confirm that a fix resolves alerts generated by custom queries or the security-extended query suite. Fix quality for alerts from third-party tools is also not guaranteed.
Getting a suggested fix with Copilot の自動修正
Copilot の自動修正 generates a single suggested fix for an alert, which you review and apply yourself.
You do not need a subscription to GitHub Copilot to use GitHub Copilotの自動修正機能, and it does not consume AI credits. Copilot の自動修正 is available to all public repositories on GitHub.com, as well as internal or private repositories owned by organizations and enterprises that have a license for GitHub Code Security.
Copilot の自動修正 is allowed by default and enabled for every repository that uses CodeQL, regardless of whether it uses default or advanced setup for code scanning. There is no separate step to enable Copilot の自動修正: enabling code scanning with CodeQL is sufficient. See コード スキャンの既定セットアップの構成.
Administrators at the enterprise, organization, and repository levels can choose to disable Copilot の自動修正. If Copilot の自動修正 has been disabled at your level, you can re-enable it by following the same steps used to disable it and selecting the option to allow Copilot の自動修正. To learn how to manage Copilot の自動修正 at each level, see コードスキャンのセキュリティアラートに対するCopilotの自動修正を無効にする.