SCA: security update for vllm (GHSA-pr7f-p5mw-fc87)

medium Tenable Cloud Security Plugin ID 474356

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. From 0.20.2rc0 until 0.26.0,
safe_load_prompt_embeds in vllm/renderers/embed_utils.py uses torch.sparse.check_sparse_tensor_invariants,
whose process-global save, enable, and restore state can be raced by concurrent prompt_embeds parts
submitted to POST /v1/chat/completions through AsyncMultiModalItemTracker.resolve_items, asyncio.gather,
and the default executor, allowing an invalid sparse tensor to reach tensor.to_dense despite the
CVE-2025-62164 guard when enable_prompt_embeds is enabled. This issue is fixed in version 0.26.0.
(CVE-2026-73557)

Solution

Update the vllm library and its related packages to version 0.26.0 or later.

Plugin Details

Severity: Medium

ID: 474356

Version: Revision 1.1

Type: Local

Family: SCA Checks

Published: 10/12/2026

Updated: 10/12/2026

Risk Information

VPR

Risk Factor: Low

Score: 3

Percentile: 23.63

Vendor

Vendor Severity: Medium

CVSS v2

Risk Factor: Medium

Base Score: 6.4

Temporal Score: 4.7

Vector: CVSS2#AV:N/AC:L/Au:N/C:P/I:P/A:N

CVSS Score Source: CVE-2026-73557

CVSS v3

Risk Factor: High

Base Score: 7.5

Temporal Score: 6.5

Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N

Temporal Vector: CVSS:3.0/E:U/RL:O/RC:C

CVSS v4

Risk Factor: Medium

Base Score: 6.3

Threat Score: 1.7

Threat Vector: CVSS:4.0/E:U

Vector: CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N

Vulnerability Information

Exploit Ease: No known exploits are available

Patch Publication Date: 9/4/2026

Vulnerability Publication Date: 8/13/2026

Reference Information

CVE: CVE-2026-73557

cwe: CWE-362

Detections

Analytics