ThreatCluster

Anthropic Fixes Remote Code Execution Flaws in Git MCP Server

First seen 21 Jan 2026, 06:39 UTC Theregister 98% similarity 23

Article Content

Browse articles
ThreatCluster

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 startup Cyata identified the exploit method.

ThreatCluster AI

Community

Browse all →