Information security
fromDEV Community
3 days agoI Let Claude Write 60 Functions. 65-75% Had Security Vulnerabilities.
AI code generation models produce insecure code by default, with no statistically significant difference among the tested models.
Cisco has presented a new open-source project designed to help make AI-generated code more secure. The initiative, called Project CodeGuard, provides a framework that allows development teams to integrate security rules directly into the workflow of AI coding tools. Examples include GitHub Copilot, Cursor, and Windsurf. AI coding agents are increasingly being used worldwide to accelerate software development and increase productivity. At the same time, the security of the generated code is often inadequate.