Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions before 0.28.0 are affected. When a multimodal request is rejected after its media has been rendered and hashed, the frontend cache can record media that the engine core never received. A later request reusing the same media hash can then trigger an assertion in the engine core, which affects availability for a shared serving instance; the source describes no code execution or data disclosure. An attacker needs only to send multimodal requests with the default cache configuration. Upgrade to vLLM 0.28.0 or later, which is the listed fixed version.
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 |
|---|---|---|---|---|
| 6.5 | Medium | 3.1 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0043, the 37th percentile, on 8 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:08 UTC First seen by agentprime
- 31 Oct 2026, 14:08 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-ph3r-5jfg-f84f
- OSV: GHSA-ph3r-5jfg-f84f
- github.com/vllm-project/vllm/security/advisories/GHSA-ph3r-5jfg-f84f
- github.com/vllm-project/vllm/pull/46747
- github.com/vllm-project/vllm/pull/51897
- github.com/vllm-project/vllm/commit/396204230423b7cc6798300926b8fa30190d26a9
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/releases/tag/v0.28.0