Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
Vulnerable: vLLM versions >=0.24.0 and <0.30.0 (fixed in 0.30.0). The Qwen2-VL and Qwen3-VL video samplers use the request-level media_io_kwargs max_frames and fps values without a ceiling, so the num_frames limit does not apply to them. An unauthenticated remote attacker who can send a chat or tokenize request can make the API server decode very large numbers of video frames, exhausting its memory and causing denial of service. The source gives few details about other affected paths beyond those noted. Upgrade to vLLM 0.30.0 or later.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 5.3 | Medium | 3.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0030, the 23rd percentile, on 9 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 23 Sept 2026, 10:25 UTC Published by the maintainers as a GitHub repository advisory
- 31 Oct 2026, 14:08 UTC First seen by agentprime
- 31 Oct 2026, 14:08 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-x6mc-67gf-chw4
- OSV: GHSA-x6mc-67gf-chw4
- github.com/vllm-project/vllm/security/advisories/GHSA-x6mc-67gf-chw4
- github.com/vllm-project/vllm/pull/56729
- github.com/vllm-project/vllm/commit/ea723c81c3ea26425cb69503a5d5e90822a04a45
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/releases/tag/v0.30.0