CVE-2024-8939

MEDIUM

Uncontrolled Resource Consumption (CWE-400)

2024-09-17 secalert@redhat.com

Denial Of Service

6.2

CVSS 3.1 · Vendor: redhat

Severity by source

Vendor (redhat) PRIMARY

6.2 MEDIUM

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

Primary rating from Vendor (redhat) · only source for this CVE.

CVSS VectorVendor: redhat

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

Attack Vector

Local

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

None

Integrity

None

Availability

High

Lifecycle Timeline

CVE Published

Sep 17, 2024 - 17:15 cve.org

MEDIUM 6.2

Blast Radius

ecosystem impact

† from your stack dependencies † transitive graph · vuln.today resolves 4-path depth

4 pypi packages depend on vllm (2 direct, 2 indirect)

Ecosystem-wide dependent count for version 0.5.0.post1.

DescriptionCVE.org

A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.

AnalysisAI

A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). Rated medium severity (CVSS 6.2), this vulnerability is no authentication required, low attack complexity. No vendor patch available.

Technical ContextAI

This vulnerability is classified as Uncontrolled Resource Consumption (CWE-400), which allows attackers to cause denial of service by exhausting system resources. A vulnerability was found in the ilab model serve component, where improper handling of the best_of parameter in the vllm JSON web API can lead to a Denial of Service (DoS). The API used for LLM-based sentence or chat completion accepts a best_of parameter to return the best completion from several options. When this parameter is set to a large value, the API does not handle timeouts or resource exhaustion properly, allowing an attacker to cause a DoS by consuming excessive system resources. This leads to the API becoming unresponsive, preventing legitimate users from accessing the service.

Affected ProductsAI

See vendor advisory for affected versions.

RemediationAI

No vendor patch is available at time of analysis. Monitor vendor advisories for updates. Implement rate limiting, set resource quotas, validate input sizes, use timeouts.