Anthropic just shipped the Claude Security plugin for Claude Code in public beta. It brings vulnerability scanning directly into your terminal workflow: scan staged changes before a commit, or sweep your entire codebase, all without leaving Claude Code. The plugin runs on the same Claude inference you're already using, so there's no separate tool to authenticate or manage.
The problem it's solving
Traditional security scanners use rule-based pattern matching. They're fast, but they work by recognizing known vulnerability signatures, which means they miss anything that doesn't fit a known pattern and tend to generate a lot of noise. Claude Security differs from conventional security products by reasoning through code more like a security researcher, rather than relying on rule-based pattern matching against known vulnerability signatures.
AI cybersecurity capabilities are advancing fast. Today's models are already highly effective at finding flaws in software code; the next generation will be more capable still, and will be particularly effective at autonomously exploiting these flaws. Now is the time for organizations to act to improve their security, preparing for a world in which working software exploits are much easier to discover. The plugin is Anthropic's answer to that urgency, putting the same capabilities on the defender's side.
How the plugin actually works
The security guidance plugin makes Claude review its own code changes for common vulnerabilities while it works and fix what it finds in the same session. Critically, it doesn't just ask the same model that wrote the code to grade itself. The reviews run as a separate Claude call with a fresh context and a security-focused prompt, so the reviewer has no investment in the original approach.
The plugin operates at three distinct layers of depth:
- Per-edit pattern check: A fast, deterministic string match that fires every time Claude writes to a file. No model call, no added cost. Catches things like
Don't miss what's next in AI
Join 300,000+ engineers and researchers who get the signal, not the noise.
- Full access to in-depth AI research breakdowns
- Be the first to know what's trending before it hits mainstream
- Daily curated papers, repos, and industry moves