Detections
Analytics
SCA: security update for vllm (GHSA-935w-9g4m-p28p)
low Tenable Cloud Security Plugin ID 472966
Description
There are packages installed that are affected by a vulnerability referenced in the following CVE:- 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. (CVE-2026-105752)
Solution
Update the vllm library and its related packages to version 0.30.0 or later.See Also
Plugin Details
Severity: Low
ID: 472966
Version: Revision 1.1
Type: Local
Family: SCA Checks
Published: 10/6/2026
Updated: 10/6/2026
Risk Information
VPR
Risk Factor: Low
Score: 1.2
Percentile: 0.01
Vendor
Vendor Severity: Low
CVSS v2
Risk Factor: Low
Base Score: 2.1
Temporal Score: 1.6
Vector: CVSS2#AV:N/AC:H/Au:S/C:N/I:P/A:N
CVSS Score Source: CVE-2026-105752
CVSS v3
Risk Factor: Low
Base Score: 3.1
Temporal Score: 2.7
Vector: CVSS:3.0/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N
Temporal Vector: CVSS:3.0/E:U/RL:O/RC:C
Vulnerability Information
Exploit Ease: No known exploits are available
Patch Publication Date: 10/6/2026
Vulnerability Publication Date: 10/5/2026
Reference Information
CVE: CVE-2026-105752