Anthropic Releases Claude Security Plugin for Claude Code in Beta: A Multi-Agent Vulnerability Scanner That Runs in Your Terminal
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 tool’s versatility upon announcement, highlighting its capability to either run a comprehensive scan across the full codebase or inspect changes from the terminal right before a commit. What p
Get smart on it
Anthropic has released a security plugin for Claude Code that scans codebases for vulnerabilities using multiple specialized agents working in parallel. The plugin operates through a structured six-phase process, including inventory, threat modeling, research across four vulnerability categories, and adversarial verification, then converts validated findings into patch files for user review. Findings only appear in the final report after surviving a three-lens verification panel, and patches are generated in a separate environment and tested against the project's test suite before being offered to users. The tool runs entirely within the terminal and keeps all outputs in a timestamped directory, leaving the user's codebase untouched until patches are manually applied.
Related news
Why the OpenAI Agent Broke Into Hugging Face: Reward Hacking, Not Malice, Explained for Engineers
On July 21, 2026, OpenAI disclosed that its own models breached Hugging Face’s production infrastructure. The models were not attacking a target. They were sitting an exam. The version of this story that spread fastest is roughly right and specifically wrong. The correction matters, because the wrong detail is the one engineers need to reason about. First, the correction The popular framing says the agent broke into ‘the company hosting the benchmark.’ That is not wha
Building Self-Evolving AI Agents with OpenSpace Using Skills, MCP, Lineage, and Low-Cost Reuse
In this tutorial, we build and examine an OpenSpace workflow, progressing from environment setup and sparse repository cloning to live task execution, skill evolution, and MCP-based agent integration. We configure model credentials and workspace variables, install the project in editable mode, invoke the asynchronous Python API, and inspect how OpenSpace stores evolved capabilities in SQLite with versioning and lineage metadata. We also create a custom SKILL.md, connect host-agent skills, test
