Threat actors could use prompt injection attacks to take advantage of three vulnerabilities in Anthropic’s official Git MCP server and cause mayhem with AI systems. This alert comes from researchers ...
Anthropic patched Git MCP flaws enabling remote code execution via tool chaining Cyata discovered CVEs; fixed in version 2025.12.18, no exploitation reported yet Claude previously manipulated in cyber ...
Three security vulnerabilities in the official Git server for Anthropic's Model Context Protocol (MCP), mcp-server-git, have been identified by cybersecurity researchers. The flaws can be exploited ...
Update, Jan 13th, 2026: Multiple Target employees have now confirmed in our follow-up report the authenticity of leaked source code sample set and shared internal announcements regarding an access ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results