Anthropic Releases New Claude Sandbox, Security Guidance Plugin
The AI giant says the new plugin, which helps developers find vulnerabilities as they write code, has been used extensively internally. The post Anthropic Releases New Claude Sandbox, Security Guidance Plugin appeared first on SecurityWeek.
Anthropic has announced two new security features for its Claude AI: a self-hosted sandbox and a new security guidance plugin.
The sandbox, currently in public beta, was announced at Anthorpic’s Code w/ Claude event in London this week.
According to the company, Claude Managed Agents can now operate in a user-controlled sandbox connected to the user’s private MPC servers.
Source: https://www.securityweek.com/anthropic-releases-new-claude-sandbox-security-guidance-plugin/
Related breach coverage
- Microsoft, Palo Alto Networks Find Many Vulnerabilities by Using AI on Their Own Code2026-05-13
Microsoft’s MDASH discovered 16 of the Patch Tuesday vulnerabilities, and Palo Alto used Mythos to find dozens of flaws. The post Microsoft, Palo Alto Networks Find Many Vulnerabilities by Using AI on Their Own Code appeared first on SecurityWeek.
- Anthropic Expanding Mythos Access to 150 New Organizations2026-06-02
Only approximately 50 companies have had access to Mythos until now and they have found thousands of vulnerabilities in their products. The post Anthropic Expanding Mythos Access to 150 New Organizations appeared first on SecurityWeek.
- 19-Year-Old Linux Kernel Vulnerability Exposes Systems to Root Access2026-06-01
Proof-of-concept (PoC) exploit code has been released for the CIFSwitch flaw, which allows low-privileged users to escalate to root on vulnerable Linux systems. The post 19-Year-Old Linux Kernel Vulnerability Exposes Systems to Root Access appeared first on SecurityWeek.
- Chrome 148 Update Patches 151 Vulnerabilities2026-05-29
The browser update resolves critical-severity security defects that could potentially lead to remote code execution. The post Chrome 148 Update Patches 151 Vulnerabilities appeared first on SecurityWeek.