ToolsThe story, in brief

Anthropic Releases Claude Security Plugin for Claude Code in Beta: A Multi-Agent Vulnerability Scanner That Runs in Your Terminal

Anthropic just shipped Claude Security—a multi-agent vulnerability scanner that turns code reviews into patch files. It's running in Claude Code beta right now.

Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI agents and the coordination of work.AI illustration by KeyNews
The KeyNews take

Why it matters

Anthropic is expanding Claude Code's surface area beyond code generation into automated security hardening. This moves Claude deeper into the developer workflow and raises the stakes for competitors offering code tools.

The key facts

5 to know
  1. Claude Security plugin released in beta for Claude Code

  2. Multi-agent vulnerability scanner runs inside Claude Code terminal sessions

  3. Generates patch files from vulnerability findings for manual review and application

  4. Tool positions Claude Code as a full-stack developer agent (generation + security audit)

  5. Security-as-a-feature differentiator vs. Cursor and GitHub Copilot

Go to the source

MarkTechPostmarktechpost.com

Publisher excerpt: Anthropic has released the Claude Security plugin for Claude Code in beta. The plugin runs a multi-agent vulnerability scan of a repository from inside an existing Claude Code session, then turns the findings you select into patch files that you review and apply yourself. Anthropic emphasized the…
Read original report
Back to today's editionMore tools news

Keep reading

Related stories

More from Tools