Making frontier cybersecurity capabilities available to defenders
What happened
Claude Code Security, a new capability integrated into Claude Code, is now available in a limited research preview for Enterprise and Team customers, with faster access for open‑source maintainers. It scans codebases for security vulnerabilities and suggests targeted patches, using AI reasoning rather than rule‑based static analysis to find complex issues like business‑logic flaws. Each finding undergoes multi‑stage verification, receives severity and confidence ratings, and appears in a dashboard for human review before any changes are applied. The tool builds on a year of research and recent testing that uncovered hundreds of previously missed vulnerabilities in open‑source projects.
Why it matters
It could help software teams fix security problems faster and more thoroughly, reducing the risk of attacks that exploit hidden bugs. By keeping the final decision with developers, it aims to improve security without automating risky changes.
Reality check
An automated, sceptical read of the sourceIncremental. The feature extends existing AI code‑analysis tools with more sophisticated reasoning, but it is presented as a preview rather than a revolutionary breakthrough.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from Anthropic
Anthropic Upgrades Claude Code Projects to Run Parallel AI Workers Hands-FreeAnthropic · 14 Nov 2026Claude designed FPGA scaler board for 6th-gen consolesAnthropic · 13 Nov 2026I asked Claude Fable 5.2 to turn my site into a 90s Silicon Graphics workstationAnthropic · 13 Nov 2026Anthropic is endorsing SB 53Anthropic · 13 Nov 2026Understanding and addressing AI harmsAnthropic · 13 Nov 2026This page was collected from anthropic.com and summarised automatically by AIPulsee's pipeline. See how it runs.