CVSS 3.1
5.3 mediumCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:LMedium (5.3) in vllm vllm. EPSS 0.3% estimated probability of exploitation activity in the next 30 days. Fixed in vllm 0.30.0.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:Lvllm (PyPI): fixed in 0.30.0Explain CVE-2026-105760 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-105760?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-105760?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-105760 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.
From the NVD's CPE matches.
| Product | Affected |
|---|---|
| vllm:vllm | from 0.23.0 before 0.30.0 |
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-58v5-2m8f-94pr | PyPI | vllm | >=0.23.0rc2 <0.30.0 | 0.30.0 |
| PYSEC-2026-4307 | PyPI | vllm | >=0.23.0rc2 <0.30.0 | 0.30.0 |
Red Hat rates this Moderate.
A moderate-impact denial of service flaw was found in the vLLM inference and serving engine, which Red Hat ships in the Red Hat AI Inference Server and Red Hat OpenShift AI (RHOAI) container images. A remote caller of the OpenAI-compatible chat completions endpoint can submit a small, valid video together with request-level media_io_kwargs that select the GLMGA video backend and very large fps and max_frames values. Because the GLMGA sampler constructs and deduplicates an attacker-sized pre-decode frame-index list without a strict work ceiling, a compact request and tiny valid video can consume disproportionate CPU time and memory in the shared media-loading executor, delaying unrelated media requests and causing service degradation or unresponsiveness. The demonstrated impact is a partial denial of service only; no memory corruption, information disclosure, or code execution is involved. The vulnerable path is reachable without vLLM credentials when no API key is configured; with API-key authentication enabled, any caller holding a valid key can trigger it. Red Hat rates this flaw MODERATE (CVSS 3.1 score 5.3, AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L), consistent with the upstream severity. Fixes for the affected Red Hat products are deferred because the impact is moderate with a CVSS score below 7.0, for which Red Hat does not file update trackers; the residual risk is limited to availability degradation of the vLLM service by callers able to reach the chat completions endpoint.
Until a fixed package is available, exposure can be reduced at the deployment level: place an authenticating API gateway or reverse proxy in front of the vLLM OpenAI-compatible chat completions endpoint that removes or filters request-level media_io_kwargs video options (video_backend, fps, and max_frames) so untrusted callers cannot select the GLMGA video sampler or supply extreme sampling values, and apply rate limiting and request concurrency limits. Note that existing media byte, pixel, or decoded-frame limits do not necessarily bound the vulnerable pre-decode frame-index allocation. The upstream project fixed this issue in vLLM 0.30.0; for the affected Red Hat products the fix is currently deferred, so restricting endpoint access to trusted callers together with the gateway measures above is the available mitigation.
| Product | Package | State | Advisory |
|---|---|---|---|
| Red Hat AI Inference Server | rhaiis/vllm-cpu-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaiis/vllm-cuda-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaiis/vllm-neuron-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaiis/vllm-rocm-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaiis/vllm-spyre-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaiis/vllm-tpu-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-cpu-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-cuda-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-gaudi-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-neuron-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-rocm-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-spyre-rhel9 | Fix deferred | |
| Red Hat AI Inference Server | rhaii/vllm-tpu-rhel9 | Fix deferred | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-aws-cuda-rhel9 | Fix deferred | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-azure-cuda-rhel9 | Fix deferred | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-azure-rocm-rhel9 | Fix deferred | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-cuda-rhel9 | Fix deferred | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-gaudi-rhel9 | Fix deferred | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-gcp-cuda-rhel9 | Fix deferred | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | rhelai3/bootc-rocm-rhel9 | Fix deferred | |
| 7 more in the JSON and on Red Hat's page. | |||
Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-105760.
The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.