CVE-2025-68143 - Vulnerability Details

Threat entity extracted from intelligence sources

Frequency
3
occurrences
First Seen
January 20, 2026
Last Seen
May 20, 2026

CVE-2025-68143 is a vulnerability tracked across 2 threat clusters and 3 intelligence report mentions on ThreatCluster. First observed January 20, 2026; most recent activity May 20, 2026.

Related Threat Clusters

  • Critical Sandbox Bypass in Claude Code Exposes User Data

    Anthropic's Claude Code AI platform has been found to have a critical network sandbox bypass vulnerability, allowing attackers to exfiltrate sensitive data, including user credentials and source code. Discovered by…

    7 articles · Updated May 20, 2026
  • Anthropic Fixes Remote Code Execution Flaws in Git MCP Server

    Anthropic has addressed three vulnerabilities in its Git MCP server, which could be exploited to remotely execute malicious code or overwrite files through prompt injection. The server connects various AI tools to Git…

    2 articles · Updated January 20, 2026

Recent Intelligence Reports

  • Second Time Same Sandbox Anthropic Claude Code Network Allowlist Bypass Data Exfiltration — oddguan.com · May 20, 2026
  • Anthropic quietly fixed flaws in its Git MCP server — Theregister · January 20, 2026
  • Anthropic quietly fixed flaws in its Git MCP server that allowed for remote code execution — Theregister · January 20, 2026

Related Entities

Data Exfiltration Anthropic Cyata CVE-2025-66479 CVE-2025-68144 CVE-2025-68145 T1041 - Exfiltration Over C2 Channel GitHub Git MCP Server Linux MacOS Mcp-server-git

CVSS v3.1 Breakdown