vllm-project · vLLM · published 2026-07-06

CVE-2026-55514vLLM denial of service via prompt embeds on M-RoPE models

Routine No exploitation evidence; EPSS 0.7%.

CVE-2026-55514 is not known to be exploited in the wild. EPSS estimates a 0.7% chance of exploitation in the next 30 days, higher than 52% of all CVEs. This vLLM vulnerability: CVSS 7.1 (v4.0). Fixed upstream in vLLM 0.24.0. Routine: patch when convenient.

Share this

Remediation#

Fixed upstream in vLLM 0.24.0.

Patch events

  1. This monthSecurity release

    AI toolingvLLM

    vLLM security release: 0.24.0

    Upgrade to 0.24.0

    Why: CVE-2026-54234: Public proof-of-concept exists (SSVC exploitation: poc).

Exploit intelligence#

SignalValueSource
Known exploitedNoCISA KEV
Ransomware use—CISA KEV
EPSS (30-day exploitation probability)0.7% (53th pct)FIRST EPSS v2026.06.15
CVSS base score7.1 (v4.0)
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
CNA / CISA ADP
SSVC exploitationnoneCISA Vulnrichment
SSVC automatableNoCISA Vulnrichment
SSVC technical impactpartialCISA Vulnrichment

Affected versions (from the CVE record)#

Description (from the CVE record)#

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is authorized to make a /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.

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 →