According to God of Prompt on X, Anthropic introduced Claude Code Security in a limited research preview to scan codebases for vulnerabilities and propose targeted patches for human review. According to Anthropic’s announcement, the tool analyzes repositories to detect issues that traditional scanners often miss and generates patch suggestions mapped to specific findings, enabling faster remediation workflows for engineering and AppSec teams. As reported by Anthropic, the system is designed for secure software development lifecycles, aiming to reduce triage time, surface high-priority risks, and support developer productivity in enterprise environments.

According to @claudeai on X, Anthropic introduced Claude Code Security in a limited research preview that scans codebases for vulnerabilities and proposes targeted software patches for human review, aiming to catch issues traditional tools miss. As reported by Anthropic via the linked announcement page, the tool is positioned to augment secure SDLC workflows by prioritizing exploitable findings and suggesting remediation diffs, which can shorten mean time to remediation for engineering teams. According to the same source, the early access focuses on accuracy with human-in-the-loop validation, indicating near-term use cases in secure code reviews, backlog triage, and compliance readiness for enterprises integrating AI-assisted application security.