CVE-2025-68143

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 researcher Aonan Guan, this flaw is the second complete bypass identified within six...

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 repositories, enabling natural language interactions for automation. The security...