Salt Security Introduces Salt Code to Enforce Security Policies in AI Coding Assistants

Salt Security has launched Salt Code, a new component of its Agentic Security Platform that enforces security policies across AI-generated code, according to a press release. The system integrates directly with AI coding assistants including Claude, Cursor, GitHub Copilot, Windsurf, Codex, and Gemini CLI, ensuring that generated code follows organizational and regulatory security standards from creation through deployment.

Salt Code operates through the company’s Posture Governance Engine, which defines and applies a unified security policy across the development lifecycle. It connects to Model Context Protocol servers used by AI coding assistants to apply security rules during code generation and extends those rules into CI/CD workflows and runtime environments. Policy violations are automatically blocked before reaching production.

The platform supports pre-built security packs covering frameworks such as OWASP API Top 10, MCP Security Top 10, and LLM Security Top 10, and allows custom organizational policies. It integrates with common developer tools including GitHub, GitLab, Bitbucket, and VS Code, as well as workflow platforms like Jira and ServiceNow.

Salt Code is available immediately to existing Salt Security customers at no additional cost and through an early access program for new users, which includes four secure coding packs.