CVE-2026-105752: vllm · Information Exposure
Affects vllmSource CVE Database V5
Not known to be exploited · CVSS 3.1 Low : upgrade to 0.30.0 when convenient.
Data as of 18 Nov 2026, 20:25 UTC
- EPSS
- 0.2% chance of exploitation in 30 days – higher than 12% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
- Patch
- Available – fixed in 0.30.0
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:NExploitation evidence
Disclosed: evidence found.
CVE published 5 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 18 Nov 2026.
What to do
Upgrade vllm and vllm-project/vllm to 0.30.0.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| vllm-projectvllm | Affected
| Fixed in
|
GitHubvllm-project/vllmpkg:github/vllm-project/vllmOther threats | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
Upgrade to vLLM version 0.30.0 or later, where this issue is fixed. No other mitigation is indicated or required as the fix addresses the root cause.
Description
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests rebuild the next-turn engine input without preserving the cache_salt value, placing the continuation prefix in the global unsalted cache namespace even when the caller enabled salting. On deployments with prefix caching enabled, which is the default, an authenticated tenant who can reconstruct a victim's low-entropy post-tool history can submit the same continuation and use the cached_tokens_per_turn count to determine whether the prefix was previously processed, defeating the intended tenant isolation of salted prefix caching. This issue is fixed in version 0.30.0.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-935w-9g4m-p28p (opens in a new tab)
- github.com/vllm-project/vllm/pull/50195 (opens in a new tab)
- github.com/vllm-project/vllm/pull/51818 (opens in a new tab)
- github.com/vllm-project/vllm/commit/6a2a2bb02b563b83f946012959fd3927984d072a (opens in a new tab)
- github.com/vllm-project/vllm/releases/tag/v0.30.0 (opens in a new tab)