Claude Security Plugin for Claude Code Now in Beta
8 hours ago
- Claude Security scans code, validates findings, and suggests patches in a seamless, user-approved workflow.
- It reasons through code like a security researcher, catching complex, multi-component vulnerabilities that pattern-matching tools miss.
- Features include parallel scanning, adversarial verification to reduce false positives, and recommended patches for human review.
- Integrates with existing workflows via webhooks to Slack/Jira, CSV/Markdown exports, and scheduled recurring scans.
- Built by Anthropic and used by their security team, it runs on the same models used to secure Anthropic's own codebase.
- Focuses on high-severity vulnerabilities such as memory corruption, injection flaws, authentication bypasses, and logic errors.
- Available in public beta for Claude Enterprise and Claude Code users, with admin console controls and a getting started guide.