Anthropic adds continuous scanning and fix tracking to Claude Security
Original title: Claude Security can now spot vulnerabilities that reappear in code
The Claude Enterprise public beta reruns scans as code changes and reopens a finding if the issue returns.
Anthropic updated Claude Security so teams can scan repositories continuously and track whether fixes remain in the code. Projects connect GitHub, GitLab, or another Git provider; a baseline scan is followed by recurring scans of risky changes, including issues spanning repositories. Findings are marked fixed when a patch lands and reopened if the issue appears again. The service is in public beta for Claude Enterprise customers and is enabled from the admin console.
- Scanning uses Anthropic’s full model family, including Claude Mythos, without Cyber Verification Program access.
- Each finding includes threat-model severity, reachability details, and sometimes an attack-path diagram.
- A new API, webhooks, and an MCP connector link findings to Claude.ai and Claude Code.
- Administrators can grant viewing and triage rights without allowing project creation.
- Vendors
- Anthropic
- Organizations
- Vanta
- AI models
- Claude Mythos
From the original article
2 min read at helpnetsecurity.com
Anthropic has updated Claude Security with ongoing code scanning and automatic fix tracking to help security teams monitor vulnerabilities as software changes. The service scans codebases for vulnerabilities and suggests patches for review. It is powered by the company’s full family of models, including Claude Mythos, without requiring Cyber Verification Program access.
By Anamarija Pogorelec · helpnetsecurity.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.