vLLM · vLLM · published 2026-06-20

CVE-2026-56340vLLM - Denial of Service via Unvalidated Multimodal Embeddings

Routine No exploitation evidence; EPSS 0.6%.

CVE-2026-56340 is not known to be exploited in the wild. EPSS estimates a 0.6% chance of exploitation in the next 30 days, higher than 51% of all CVEs. This vLLM vulnerability: CVSS 8.7 (v4.0), a successful attack gives total control of the component. Fixed upstream in vLLM 0.13.0. Routine: patch when convenient.

Share this

Remediation#

Fixed upstream in vLLM 0.13.0.

Patch events

  1. This monthSecurity release

    AI toolingvLLM

    vLLM security release: 0.13.0

    Upgrade to 0.13.0

    Why: Vendor security release for server software (most severe: CVE-2026-56340).

Exploit intelligence#

SignalValueSource
Known exploitedNoCISA KEV
Ransomware use—CISA KEV
EPSS (30-day exploitation probability)0.6% (52th pct)FIRST EPSS v2026.06.15
CVSS base score8.7 (v4.0)
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CNA / CISA ADP
SSVC exploitationnoneCISA Vulnrichment
SSVC automatableNoCISA Vulnrichment
SSVC technical impacttotalCISA Vulnrichment

Affected versions (from the CVE record)#

Description (from the CVE record)#

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.

Quoted from the CVE Program record.

Elsewhere#

Distro status: Debian · Ubuntu · Red Hat · Alpine

Something wrong on this page?
Anonymous. Reports are checked against the primary source.

Also on today's list

See today's list → · Coming up →