CVE Intelligence
Skip to main content
MEDIUM

CVE-2026-105754

CVE-2026-105754 — vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.

Published Updated Sources: cvelistV5, GitHub_M

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the scoring sources call it.

Exploitation

Unreported

no source claims exploitation

EPSS

0%

chance of exploitation in 30 days

Affects

vllm project

vllm

CVSS base

6.5

MEDIUM

CISA SSVC assessment

Three decision points CISA publishes for the CVEs it assesses · SSVC 2.0.3. A stakeholder decision, not a severity score.

CISA

Exploitation

None

none · proof-of-concept · active

Automatable

No

can an attacker script all four kill-chain steps

Technical impact

Partial

partial · total control of the vulnerable component

Affected scope

The catalog records vendors and products as separate lists, not pairs, so which product belongs to which vendor is not something this page can say.

Vendors (1)

vllm project

Products (1)

vllm

Every base score collected

Sources score independently and disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactSource
6.5CVSS 3.1MEDIUM——cvelistV5

Weakness & attack patterns

  • CWE-20
  • CWE-617
  • CWE-639
  • CWE-668
  • CWE-704
  • CWE-1284

Attack patterns reported against this CVE. The ATT&CK techniques below are inferred from its weakness class.

  • T1562.003Impair Defenses: Impair Command History Logging
  • T1574.006Hijack Execution Flow: Dynamic Linker Hijacking
  • T1574.007Hijack Execution Flow: Path Interception by PATH Environment Variable

Detection

Read off the CVSS vector and the weakness class. Starting points, not rules we have tested.

  • Search application, proxy, and WAF logs for requests touching /inference/v1/generate.

References

4 on the record

Elsewhere on this site

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.