VDB
CVE-2026-105760
CVE-2026-105760
PUBLISHED
CVSS 5.3 MEDIUM
Reported by GitHub_M · Published October 5, 2026
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.
Risk Scores
CVSS 3.1
5.3
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.23.0rc2, < 0.30.0 |
| PyPI | vllm | 0.23.0-rc.2 |
| chainguard | tritonserver-backend-vllm-cuda-13.0 | 0 |
| chainguard | vllm-cuda-13.2 | 0 |
| chainguard | vllm-openai-cuda-13.0 | 0 |
| vllm-project | vllm | 0.23.0rc2 |
Timeline
- Oct 5, 2026 CVE Published
- Oct 6, 2026 EPSS Score
- Oct 6, 2026 Coalition ESS Score
- Oct 6, 2026 CVE Updated
- Oct 9, 2026 EPSS Score
- Oct 13, 2026 EPSS Score
- Oct 15, 2026 EPSS Score
- Oct 17, 2026 EPSS Score
- Oct 20, 2026 EPSS Score
- Oct 21, 2026 EPSS Score
- Oct 24, 2026 EPSS Score
- Oct 25, 2026 EPSS Score
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94pr x_refsource_CONFIRM
- https://github.com/vllm-project/vllm/pull/54935 x_refsource_MISC
- https://github.com/vllm-project/vllm/commit/8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7 x_refsource_MISC
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0 x_refsource_MISC
- https://nvd.nist.gov/vuln/detail/CVE-2026-105760 advisory
- https://github.com/advisories/GHSA-58v5-2m8f-94pr advisory