Automated Security Reviews Launched in Claude Code

• Anthropic has launched automated security reviews for Claude Code.
• The /security-review function allows for the detection of vulnerabilities in the code.
• Tools can be integrated into the developers' workflows without additional resources.

This is reported by ZDNet, VentureBeat.

Key Takeaways from ZDNET

• Automated security reviews in Claude Code help ensure code safety.
• Developers can identify and fix vulnerabilities before code deployment.
• The /security-review command can be run in the terminal or via GitHub Action.

On September 6, 2025, Anthropic announced the launch of automated security reviews for Claude Code. These new features allow developers to quickly identify vulnerabilities in code and propose fixes.

The update includes the ability to run the /security-review command in the terminal, which activates security analysis. Claude Code checks the code for common vulnerabilities such as SQL injection risks and data processing errors.

Thanks to this function, developers can integrate security reviews into their workflows, allowing them to identify problems even before the code reaches the main branch.

Additionally, the new GitHub Action feature allows for automated analysis of each pull request for vulnerabilities, enhancing code security controls.

According to Logan Graham, an engineer at Anthropic, these tools assist developers, even in small teams, in improving security practices simply by integrating them into their existing workflows.

Studies show that increased use of artificial intelligence for code writing raises security risks, making it essential to have effective tools for their mitigation.

Access to New Features

To utilize the /security-review command, developers need to update Claude Code to the latest version and run the command in their project.

Tags: Technology/AI