Skip to content
NewA calmer, faster ZeroHour
StoryAI tools & infrainfo

Claude Security beta tracks fixes and reopens returning bugs

2 sources · 2 articlesFirst reported Updated ()
What's new

October 22: reports add automatic reopening of returning findings, multi-provider Git connections, an API, webhooks and MCP, and an unconfirmed claim of more than one million vulnerabilities since April.

Merged summary · x-ai/grok-4.7 · rewritten as coverage arrivesSummaries by Vani AI

Claude Security’s Enterprise public beta now rescans changing repositories, marks fixes, and reopens findings if the issue returns.

Anthropic updated Claude Security so Enterprise teams can scan connected repositories continuously and track whether fixes stay in the code. Projects connect the Claude GitHub app, including GitHub Enterprise Server, or use tokens for GitLab and other Git providers. A baseline scan is followed by later checks of risky changes, including issues that span repositories; there is no fixed schedule. Findings are marked fixed when a correction is detected and reopened if the issue returns. The service remains in public beta, is enabled from the admin console, and uses Claude models including Claude Mythos without Cyber Verification Program access. Anthropic says users have found more than one million vulnerabilities since April; that figure is unconfirmed.

Key facts
  • Public beta for Claude Enterprise customers, enabled from the admin console.
  • Baseline scan, then risk-based rechecks with no fixed schedule.
  • Findings marked fixed when a patch lands and reopened if the issue returns.
  • Supports Claude GitHub app, GitHub Enterprise Server, GitLab, and other Git providers.
  • Anthropic claims more than one million vulnerabilities found since April; unconfirmed.
  • Uses Claude models including Mythos, without Cyber Verification Program access.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

What each outlet adds

beyond the shared facts
  • Help Net SecurityAdmins can grant view and triage rights without project creation; some findings include attack-path diagrams.
  • Cyber Security NewsNo fixed schedule; results can vary; proposed fixes should be reviewed; unconfirmed million-vulnerability claim.
Vendors
Anthropic
Products
Claude SecurityClaude CodeClaude.ai
Organizations
Vanta
AI models
Claude Mythos

Coverage

oldest first · one row per article · UTC
  1. · 3d ago Help Net SecurityFirst report

    Anthropic adds continuous scanning and fix tracking to Claude Security

    The Claude Enterprise public beta reruns scans as code changes and reopens a finding if the issue returns.

  2. · 3d ago Cyber Security News

    Claude Security adds continuous repository scans in public beta

    Enterprise customers get automatic rechecks that mark fixes and reopen recurring findings, with no fixed scan schedule.