Description
Cursor is a code editor built for programming with AI. In versions 1.2.4 and below, attackers can achieve remote and persistent code execution by modifying an already trusted MCP configuration file inside a shared GitHub repository or editing the file locally on the target's machine. Once a collaborator accepts a harmless MCP, the attacker can silently swap it for a malicious command (e.g., calc.exe) without triggering any warning or re-prompt. If an attacker has write permissions on a user's active branches of a source repository that contains existing MCP servers the user has previously approved, or allows an attacker has arbitrary file-write locally, the attacker can achieve arbitrary code execution. This is fixed in version 1.3.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| cursor | cursor | < 1.3 | — |
Public exploits
Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.
GitHub 4 repositories
-
glebgorelikov-droid/agentgate ★ 0 · Nov 10, 2026
Integrity layer for MCP tool surfaces: pre-install vetting, cryptographic pinning, drift detection (CVE-2025-54136 class). Local-first, zero-egress, Apache-2.0.
-
GeeksikhSecurity/ai-tool-poisoning-guard ★ 0 · Sep 7, 2026
Free security-baseline rule for Claude Code, Codex, and Cursor: treats MCP tool descriptions as untrusted input (OWASP MCP Top 10 MCP03, CVE-2025-54136).
-
Sushank05/mcp-doorman ★ 0 · Jul 8, 2026
A lightweight mcp to prevent poisoning CVE (CVE-2025-54136), researchers hijacking Claude Code/Copilot/Gemini via prompt injection, and hundreds of MCP servers exposed with zero auth, this mcp protec…
-
PRE5T0/CVE-2025-54136 ★ 0 · Jan 15, 2026
CVE-2025-54136 PoC
Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.