CVE-2025-54136
Remote Code Execution in Cursor AI Code Editor via malicious MCP servers
Executive Summary
CVE-2025-54136 is a critical severity vulnerability affecting ai-code, appsec. It is classified as Code Injection. Ensure your systems and dependencies are patched immediately to mitigate exposure risks.
Precogs AI Insight
"This critical flaw stems from within Remote Code Execution, allowing the absence of comprehensive security boundaries. An attacker can craft a specific payload to compromise the entire application stack, rendering traditional defenses ineffective. The Precogs detection suite automatically flags these architectural defects to neutralize the threat at the source level."
What is this vulnerability?
CVE-2025-54136 is categorized as a critical Code Injection / RCE flaw. Based on our vulnerability intelligence, this issue occurs when the application fails to securely handle untrusted data boundaries.
Remote Code Execution in Cursor AI Code Editor via malicious MCP servers. CVSS 9.8 — Critical RCE in popular AI coding assistant via Model Context Protocol server po.
This architectural defect enables adversaries to bypass intended security controls, directly manipulating the application's execution state or data layer. Immediate strategic intervention is required.
Risk Assessment
| Metric | Value |
|---|---|
| CVSS Base Score | 9.8 (CRITICAL) |
| Vector String | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H |
| Published | March 21, 2026 |
| Last Modified | March 21, 2026 |
| Related CWEs | CWE-94, CWE-502 |
Impact on Systems
✅ Remote Code Execution: Attackers achieve arbitrary command execution within the context of the application server.
✅ Privilege Escalation: Initial code execution can be exploited to pivot and elevate privileges across the network.
✅ Persistent Backdoors: Attackers can bind reverse shells, modify source files, or inject persistent access mechanisms.
How to fix this issue?
Implement the following strategic mitigations immediately to eliminate the attack surface.
1. Remove Dynamic Evaluation Completely eliminate the use of dynamic evaluation functions (eval(), exec(), system()) on untrusted input.
2. Sandboxing If dynamic execution is an absolute business requirement, isolate the execution environment in tightly constrained, non-networked sandboxes (e.g., restricted WebAssembly or isolated containers).
3. Network Segmentation Restrict outbound traffic from the application server (egress filtering) to prevent reverse shell connections.
Vulnerability Signature
// Vulnerable Node.js Execution
const exec = require('child_process').exec;
const user_domain = req.query.domain;
// VULNERABLE: Injecting user input directly into system shell commands
exec('ping -c 4 ' + user_domain, (error, stdout, stderr) =\> \{
res.send(stdout);
\});
// EXPLOIT PAYLOAD: precogs.ai ; cat /etc/passwd
References and Sources
- NVD — CVE-2025-54136
- MITRE — CVE-2025-54136
- CWE-94 — MITRE CWE
- CWE-94 Details
- CWE-502 — MITRE CWE
- CWE-502 Details
- AI Code Security Vulnerabilities
- Application Security Vulnerabilities
Vulnerability Code Signature
Attack Data Flow
| Stage | Detail |
|---|---|
| Source | Untrusted payload via API or file upload |
| Vector | Input passed to a dynamic code evaluation function |
| Sink | eval(), exec(), or similar unsafe execution sink |
| Impact | Remote Code Execution (RCE), full system compromise |
Vulnerable Code Pattern
# ❌ VULNERABLE: Dynamic code evaluation
def process_data(user_input):
# Taint sink: arbitrary code execution
result = eval(user_input)
return result
Secure Code Pattern
# ✅ SECURE: Safe parsing
import ast
def process_data(user_input):
# Sanitized parsing: only evaluates literal structures
result = ast.literal_eval(user_input)
return result
How Precogs Detects This
Precogs AI Analysis Engine identifies unsafe dynamic code evaluation paths by tracking untrusted data into sinks like eval() and exec().\n