Three Flaws in Anthropic MCP Git Server Enable File Access and Code Execution
Summary: Three vulnerabilities were disclosed in mcp-server-git, Anthropic's official Git Model Context Protocol server, allowing arbitrary file reads and deletes and code execution, and were fixed in versions 2025.9.25 and 2025.12.18 after disclosure in June 2025. Cyata researcher Yarden Porat said the flaws are exploitable through prompt injection, so an attacker who influences what an AI assistant reads, such as a malicious README or poisoned issue description, can weaponize them without direct access to the victim's system.
What you should know: Cyata chained the three flaws with the Filesystem MCP server to write a .git/config file and reach remote code execution via a prompt injection, and its CEO Shahar Tal noted the flaws work out of the box in the reference implementation developers are expected to copy.
Read the original at The Hacker News ↗
- Topics
- AI Security
- Related
- SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 8 Cyber Risks · Nov 15, 2026Pentagon Renames CDAO ‘Super Intelligence Office’ Cyber Risks · Nov 15, 2026186 Fake AI Domains Redirect Users to Click Fix Lures, Browser Malware, and Search Hijackers Cyber Risks · Nov 12, 2026