CVE-2026-55514
Vllm 0.12.0 – 0.24.0
Raw vector
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/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:XSummary
CVE-2026-55514 is a high-severity Reachable Assertion (CWE-617) vulnerability in Vllm Vllm. Its CVSS base score is 7.1 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Application or System Exploitation (T1499.004); ranked at the 30th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as LLM Application Platforms.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SA-8 (Security and Privacy Engineering Principles) — see the control section below for these in your framework.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-41925
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- N/A
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: llm
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation finds reachable assertions during development.
Security engineering principles discourage use of assertions for handling untrusted input.
Validating untrusted inputs structurally prevents attacker data from reaching and triggering assertions.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices directly prevent unsafe assertions from being coded in reachable paths.
Runtime monitoring of software can detect assertion-triggered crashes as adverse events.
Vulnerability identification processes can discover and record reachable-assertion flaws before deployment.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing in development can detect reachable assertions before release, reducing the likelihood of exploitation.
Secure development lifecycle mandates defensive coding and input validation that prevent reachable assertions from being triggered by untrusted data.
Application security requirements can specify that assertions must not be reachable from attacker-controlled inputs.
Secure architecture principles discourage the use of assertions for runtime error handling that an attacker could exploit.
Secure coding standards explicitly ban the use of assert() or equivalent statements that can be triggered by external input.