HighVulnerabilityLLM-specific
CVE-2026-55514: vLLM crash via pure prompt embeds in /v1/completions requests
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-55514
- Published
- Record updated
- Affected
- vllm >= 0.12.0, < 0.24.0
- Fixed in
- 0.24.0
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.7%
Summary
CVE-2026-55514 affects vLLM, a library for LLM inference and serving, in versions from 0.12.0 to before 0.24.0. Sending a pure prompt embeds payload in a /v1/completions request to a model using M-RoPE makes EngineCore fail an assertion and crash, shutting down the entire server application. Any remote user authorized to make a /v1/completions request can trigger it.
Mitigation
This issue is fixed in version 0.24.0.
Affected packages in the Exposure Registry
Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.
- vllmPyPILLM dependency since 2023-08-25 · 15 tracked dependents
Topics
Related items
- MediumCVE-2026-109311: vLLM audio upload heap overflow via FFmpeg IAMF parserSimilar attack · NVD/CVE Database
- MediumCVE-2026-108748: Quarkus LangChain4j memory exhaustion in chat-scopes WebSocketSimilar attack · NVD/CVE Database
- HighHermes Agent - Pre-Authentication Disk ConsumptionSimilar attack · Tenable Research Advisories
- MediumHermes Agent - Pre-Authentication Memory ExhaustionSimilar attack · Tenable Research Advisories
- MediumGHSA-v36g-jcw9-x7cw: Pydantic AI: Excessive resource use when local web fetching converts nested HTMLSimilar attack · GitHub Advisory Database