Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions before 0.30.0 are affected. When a GPT-OSS Harmony request on the Responses endpoint uses a built-in or MCP tool, the follow-up turns after each tool call drop the caller's cache_salt, so their prompt prefixes are cached in the shared unsalted namespace. An authenticated user on a shared deployment who can guess the post-tool history may be able to learn, from per-turn cached-token counts, whether another tenant processed that prompt. Upgrade to vLLM 0.30.0 or later, which contains the fix.
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 |
|---|---|---|---|---|
| 3.1 | Low | 3.1 | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0022, the 12th percentile, on 5 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-935w-9g4m-p28p
- OSV: GHSA-935w-9g4m-p28p
- github.com/vllm-project/vllm/security/advisories/GHSA-935w-9g4m-p28p
- github.com/vllm-project/vllm/pull/50195
- github.com/vllm-project/vllm/pull/51818
- github.com/vllm-project/vllm/commit/6a2a2bb02b563b83f946012959fd3927984d072a
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/releases/tag/v0.30.0