CVE-2026-55514
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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.66%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
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.
- CVSS 4.0
- 7.1 HIGHCVSS: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/M
- EPSS
- 0.66% probability · 50th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-617
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
References
- https://github.com/vllm-project/vllm/commit/470229c37efaf69c86e8bc97482b0b1ff7551c65Patch
- https://github.com/vllm-project/vllm/pull/45252Issue Tracking, Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.24.0Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-33cg-gxv8-3p8gVendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.