CVE-2026-55514
published 2026-07-06CVE-2026-55514: 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…
PriorityP336medium6.5CVSS 3.1
AVNACLPRLUINSUCNINAH
EPSS
0.37%
30.1th percentile
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.
Affected
23 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| rhaii | vllm-cpu-rhel9 | — | — |
| rhaii | vllm-cuda-rhel9 | — | — |
| rhaii | vllm-gaudi-rhel9 | — | — |
| rhaii | vllm-neuron-rhel9 | — | — |
| rhaii | vllm-rocm-rhel9 | — | — |
| rhaii | vllm-spyre-rhel9 | — | — |
| rhaii | vllm-tpu-rhel9 | — | — |
| rhaiis | vllm-cpu-rhel9 | — | — |
| rhaiis | vllm-cuda-rhel9 | — | — |
| rhaiis | vllm-rocm-rhel9 | — | — |
| rhaiis | vllm-tpu-rhel9 | — | — |
| rhelai3 | bootc-aws-cuda-rhel9 | — | — |
| rhelai3 | bootc-azure-cuda-rhel9 | — | — |
| rhelai3 | bootc-azure-rocm-rhel9 | — | — |
| rhelai3 | bootc-cuda-rhel9 | — | — |
| rhelai3 | bootc-gaudi-rhel9 | — | — |
| rhelai3 | bootc-gcp-cuda-rhel9 | — | — |
| rhelai3 | bootc-rocm-rhel9 | — | — |
| rhoai | odh-llm-d-kv-cache-rhel9 | — | — |
| rhoai | odh-vllm-gaudi-rhel9 | — | — |
| vllm-project | vllm | — | — |
| vllm | vllm | >= 0.12.0 < 0.24.0 | 0.24.0 |
| vllm | vllm | >= 0.12.0 < 0.24.0 | 0.24.0 |
CVSS provenance
nvdv3.16.5MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
nvdv4.07.1HIGHCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
vendor_redhat6.5MEDIUM
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
GHSA
vLLM denial of service via prompt embeds on M-RoPE models
ghsa·2026-07-20
CVE-2026-55514 [HIGH] CWE-617 vLLM denial of service via prompt embeds on M-RoPE models
vLLM denial of service via prompt embeds on M-RoPE models
### Summary
_Short summary of the problem. Make the impact and severity as clear as possible. For example: An unsafe deserialization vulnerability allows any unauthenticated user to execute arbitrary code on the server._
Sending a pure prompt embeds payload in a `/v1/completions` request with a model using M-RoPE causes the 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` endpoint can trivially make such a request and induce a crash.
### Details
_Give all details on the vulnerability. Pointing to the incriminated source code is very helpful for the maintainer._
In commit [56669c1](https://github.com/vllm-project/vllm/com
VulDB
vllm-project vLLM up to 0.23.x EngineCore assertion
vuldb·2026-07-06·CVSS 7.1
CVE-2026-55514 [HIGH] vllm-project vLLM up to 0.23.x EngineCore assertion
A vulnerability described as problematic has been identified in vllm-project vLLM up to 0.23.x. This impacts an unknown function of the component EngineCore. Executing a manipulation can lead to reachable assertion.
This vulnerability appears as CVE-2026-55514. The attack may be performed from remote. There is no available exploit.
Red Hat
vllm: vLLM: Denial of Service via crafted prompt in /v1/completions request
vendor_redhat·2026-07-06·CVSS 6.5
CVE-2026-55514 [MEDIUM] CWE-617 vllm: vLLM: Denial of Service via crafted prompt in /v1/completions request
vllm: vLLM: Denial of Service via crafted prompt in /v1/completions request
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.
A flaw was found in vLLM, a library for Large Language Model (LLM) inference and serving. A remote attacker, authorized to make a /v1/completions request, can send a specially crafted prompt embeds payload. This action causes the EngineCore to fail an assertion and fatally crash, leading to a Den
No detection rules found.
No public exploits indexed.
2026-07-06
Published