Anthropic Launches Claude Code Security for AI-Powered Vulnerability Scanning
The Hacker News • • business
Key Points:
- Anthropic has launched Claude Code Security, an AI-powered feature that scans software codebases for vulnerabilities and suggests patches, currently available in limited preview for Enterprise and Team customers.
- The tool aims to help developers find and fix security issues that traditional methods might miss by reasoning through code interactions and data flows like a human security researcher.
- Claude Code Security includes a multi-stage verification process to filter false positives and assigns severity ratings to prioritize critical vulnerabilities.
- The system operates with a human-in-the-loop approach, providing confidence ratings for findings and requiring human approval before any patches are applied.
- Anthropic developed this feature to counteract AI-enabled attacks where adversaries use similar tools to discover exploitable weaknesses faster than conventional methods.
