vLLM up to 0.17.0 Media Fetching multimodal/inputs.py AsyncMediaIO.fetch_audio/AsyncMediaIO.fetch_image memory allocation
| CVSS Meta Temp Score | Current Exploit Price (≈) | CTI Interest Score |
|---|---|---|
| 4.2 | $0-$5k | 1.57 |
Summary
A vulnerability was found in vLLM up to 0.17.0. It has been classified as problematic. Affected by this vulnerability is the function AsyncMediaIO.fetch_audio/AsyncMediaIO.fetch_image of the file multimodal/inputs.py of the component Media Fetching. The manipulation leads to memory allocation.
This vulnerability is uniquely identified as CVE-2026-37237. The attack is possible to be carried out remotely. No exploit exists.
Details
A vulnerability was found in vLLM up to 0.17.0. It has been rated as problematic. This issue affects the function AsyncMediaIO.fetch_audio/AsyncMediaIO.fetch_image of the file multimodal/inputs.py of the component Media Fetching. The manipulation with an unknown input leads to a memory allocation vulnerability. Using CWE to declare the problem leads to CWE-789. The product allocates memory based on an untrusted, large size value, but it does not ensure that the size is within expected limits, allowing arbitrary amounts of memory to be allocated. Impacted is availability. The summary by CVE is:
vLLM up to and including 0.17.0 allows remote attackers to cause a Denial of Service via memory exhaustion. The AsyncMediaIO.fetch_audio and AsyncMediaIO.fetch_image functions in multimodal/inputs.py fetch user-supplied media URLs using aiohttp and call r.read() without enforcing a maximum response size, allowing an attacker to exhaust server memory by providing a URL to an arbitrarily large file.
The advisory is shared at github.com. The identification of this vulnerability is CVE-2026-37237 since 04/06/2026. The exploitation is known to be easy. The attack may be initiated remotely. Technical details are known, but no exploit is available.
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.
Product
Name
Version
CPE 2.3
CPE 2.2
CVSSv4
VulDB Vector: 🔒VulDB Reliability: 🔍
CVSSv3
VulDB Meta Base Score: 4.3VulDB Meta Temp Score: 4.2
VulDB Base Score: 4.3
VulDB Temp Score: 4.2
VulDB Vector: 🔒
VulDB Reliability: 🔍
CVSSv2
| AV | AC | Au | C | I | A |
|---|---|---|---|---|---|
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| 💳 | 💳 | 💳 | 💳 | 💳 | 💳 |
| Vector | Complexity | Authentication | Confidentiality | Integrity | Availability |
|---|---|---|---|---|---|
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
| Unlock | Unlock | Unlock | Unlock | Unlock | Unlock |
VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍
Exploiting
Class: Memory allocationCWE: CWE-789 / CWE-400 / CWE-404
CAPEC: 🔒
ATT&CK: 🔒
Physical: No
Local: No
Remote: Yes
Availability: 🔒
Status: Not defined
Price Prediction: 🔍
Current Price Estimation: 🔒
| 0-Day | Unlock | Unlock | Unlock | Unlock |
|---|---|---|---|---|
| Today | Unlock | Unlock | Unlock | Unlock |
Threat Intelligence
Interest: 🔍Active Actors: 🔍
Active APT Groups: 🔍
Countermeasures
Recommended: no mitigation knownStatus: 🔍
0-Day Time: 🔒
Timeline
04/06/2026 CVE reserved08/28/2026 Advisory disclosed
08/28/2026 VulDB entry created
08/28/2026 VulDB entry last update
Sources
Advisory: github.comStatus: Not defined
CVE: CVE-2026-37237 (🔒)
GCVE (CVE): GCVE-0-2026-37237
GCVE (VulDB): GCVE-100-396737
Entry
Created: 08/28/2026 17:48Changes: 08/28/2026 17:48 (54)
Complete: 🔍
Cache ID: 216::103
Several companies clearly confirm that VulDB is the primary source for best vulnerability data.
No comments yet. Languages: en.
Please log in to comment.