vLLM up to 0.5.2.2 /v1/completions use_beam_search best_of resource consumption

Summaryinfo

A vulnerability, which was classified as problematic, has been found in vLLM up to 0.5.2.2. The impacted element is the function use_beam_search of the file /v1/completions. The manipulation of the argument best_of leads to resource consumption. This vulnerability is traded as CVE-2024-11040. It is possible to initiate the attack remotely. There is no exploit available.

Detailsinfo

A vulnerability was found in vLLM up to 0.5.2.2. It has been rated as critical. This issue affects the function use_beam_search of the file /v1/completions. The manipulation of the argument best_of with an unknown input leads to a resource consumption vulnerability. Using CWE to declare the problem leads to CWE-400. The product does not properly control the allocation and maintenance of a limited resource, thereby enabling an actor to influence the amount of resources consumed, eventually leading to the exhaustion of available resources. Impacted is availability. The summary by CVE is:

vllm-project vllm version 0.5.2.2 is vulnerable to Denial of Service attacks. The issue occurs in the 'POST /v1/completions' and 'POST /v1/embeddings' endpoints. For 'POST /v1/completions', enabling 'use_beam_search' and setting 'best_of' to a high value causes the HTTP connection to time out, with vllm ceasing effective work and the request remaining in a 'pending' state, blocking new completion requests. For 'POST /v1/embeddings', supplying invalid inputs to the JSON object causes an issue in the background loop, resulting in all further completion requests returning a 500 HTTP error code ('Internal Server Error') until vllm is restarted.

The advisory is shared at huntr.com. The identification of this vulnerability is CVE-2024-11040 since 11/09/2024. The exploitation is known to be easy. The attack may be initiated remotely. No form of authentication is needed for a successful exploitation. Technical details are known, but no exploit is available. MITRE ATT&CK project uses the attack technique T1499 for this issue.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Productinfo

Name

• vLLM

Version

• 0.5.2.0
• 0.5.2.1
• 0.5.2.2

CPE 2.3info

• 🔍
• 🔍
• 🔍

CPE 2.2info

• 🔍
• 🔍
• 🔍

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Discussion