vLLM: Uncontrolled Resource Consumption
CVE-2026-90554 is a high-severity uncontrolled resource consumption vulnerability in vLLM from Vllm-project, with a CVSS 3.1 base score of 7.5 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, without any action from a user. The record lists version 0.28.0 as the first without the flaw, so updating vLLM to that release or later removes the exposure. There is no confirmed exploitation so far. EPSS estimates a 0.2% chance of exploitation within 30 days, which is low compared with other CVEs.
High severity with no evidence of exploitation so far.
What to do
- Update vLLM to 0.28.0 or a later version.
- Read the advisory on github.com for workarounds and exact fixed builds.
- Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.
Affected products and versions
| Vendor | Product | Affected versions | Fixed in |
|---|---|---|---|
| Vllm-project | vLLM | 0.10.2 up to, but not including, 0.28.0 | 0.28.0 |
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- NetworkCan be exploited remotely over a network, including the internet.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- NoneNo account or login is needed.
- User interaction
- NoneNo action by a victim is required.
- Scope
- UnchangedImpact stays within the vulnerable component.
- Confidentiality
- NoneNo data is disclosed.
- Integrity
- NoneNothing can be modified.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H. Scored by NVD.
| Scoring system | Score | Severity | Scored by |
|---|---|---|---|
| CVSS 4.0 | 6.9 | Medium | CNA (vulncheck.com) |
| CVSS 3.1 | 6.2 | Medium | CNA (vulncheck.com) |
| CVSS 3.1 | 7.5 | High | NVD |
Official description
vLLM versions >=0.10.2 and <0.28.0 do not apply any audio decode-size or duration limit when extracting audio from video input for NanoNemotronVL models. In nano_nemotron_vl.py, _extract_audio_from_videos calls load_audio_pyav(BytesIO(video_bytes)) without the max_duration_s or max_decode_bytes parameters, so neither VLLM_MAX_AUDIO_DECODE_DURATION_S nor VLLM_MAX_AUDIO_DECODE_BYTES is enforced (unlike the direct audio upload path in AudioMediaIO). When a NanoNemotronVL model is served with use_audio_in_video=True, an attacker who supplies a small, highly compressed video as multimodal input can force the server to allocate gigabytes of memory during audio decoding, resulting in a denial of service. Fixed in vLLM 0.28.0.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Uncontrolled Resource Consumption
The product does not properly control the allocation and maintenance of a limited resource.
How developers prevent this class of flaw
- Ensure that protocols have specific limits of scale placed on them.
- Ensure that all failures in resource allocation place the system into a safe posture.
More Uncontrolled Resource Consumption vulnerabilities (CWE-400)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: none, automatable: no, technical impact: partial).
- Record last changed materially (score, affected products, status or references).
References
Third-party and government advisories
Other vulnerabilities in vLLM
- 7.5 High severity
- 9.8 Critical severity
- 8.8 High severity
- 7.7 High severity
- 7.5 High severity
- 7.5 High severity
Recent Uncontrolled Resource Consumption vulnerabilities
- 7.5 High severity
- 7.5 High severity
- 7.5 High severity
- 7.5 High severity
- 7.5 High severity
- 7.5 High severity
Spotted an error? Tell us.