Type: url
Original: https://www.anthropic.com/news/claude-code-security
Status: generated
Language: en
Summary
Anthropic announces Claude Code Security, a capability built into Claude Code on the web and released as a limited research preview, which scans codebases for vulnerabilities by reasoning about how code behaves rather than matching known patterns, re-checks its own findings, and suggests patches that are applied only with human approval. It is offered to Enterprise and Team customers, with free expedited access for open-source maintainers, and builds on the Frontier Red Team’s research into Claude’s cybersecurity capabilities.