Dashboard / CVE-2026-115912

CVE-2026-115912

HIGH
MEDIUM Priority: 0.04 BB Relevance: 68/100
Published: 2026-10-26 Modified: 2026-10-28 First seen: 2026-10-29 Status: active

Attack Surface

Network Low Complexity No Interaction Conf. Impact Integ. Impact

CVSS Vector Breakdown

AV: Network
AC: Low
PR: Low
UI: None
S: Unchanged
C: High
I: High
A: High

Description

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0.

Weakness Classification (1)

Affected Software (1)

VendorProductVersion
vllm vllm < 0.32.0

References & Advisories (4)

Bug Bounty Relevance

68 / 100
✓ Network accessible
✓ Low complexity
✓ No user interaction

CVSS Score

8.8 / 10.0 v3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

EPSS — Exploitation Probability

0.51%
Raw Score 0.005100
Percentile 43.4%
Date 2026-10-29

EPSS Trend

2026-10-29
0.00510
2026-10-28
0.00481

Intelligence Sources

mitre ref →
nvd ref →

External Links