CVE-2026-90553
Vllm ≤ 0.28.0
Raw vector
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/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:XCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). EPSS, Forum of Incident Response and Security Teams (FIRST), epss.first.org. Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2026-90553 is a high-severity Code Injection (CWE-94) vulnerability in Vllm. Its CVSS base score is 8.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Privilege Escalation (T1068); ranked at the 24th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
The strongest mitigations our analysis identified map to AC-6 (Least Privilege) and SA-11 (Developer Testing and Evaluation) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-76871
Vulnerability Data
vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process…
more
authority even when trust_remote_code is set to False.
- CWE(s)
Related Threats
MITRE ATT&CK Enterprise Techniques
MITRE ATT&CK v20.0
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.3.1
Mitigating Controls (NIST 800-53 r5)
Our mappings, made for this CVE.
Least privilege limits the damage an injected code fragment can perform once executed.
Developer testing and evaluation finds code paths that accept and execute externally influenced strings.
Requiring documented secure development standards and tools enforces use of safe code-generation APIs and escaping.
Input validation directly stops untrusted data from being used to construct executable code without neutralization.
Mitigating Controls (NIST CSF 2.0)
Our mappings, derived directly from the weakness types (CWEs) cited in the NVD entry via our CWE→CSF cross-walk — links open the control.
PR.PS-06's SDLC practices directly target injection flaws via secure coding and testing (mostly), yet as a single broad outcome it leaves many code-generation specifics unaddressed (partial).
Mitigating Controls (ISO/IEC 27001:2022 Annex A)
Our mappings, derived directly from the weakness types (CWEs) cited in the NVD entry via our CWE→ISO cross-walk — links open the control.
Banning unapproved code samples and unauthenticated web services, combined with secure-coding standards and SAST, prevents the dynamic generation or inclusion of attacker-supplied code.
A.8.8's reach is DISCLOSURE — it sees only instances that carry a vendor-published flaw in third-party components. CWE-94 (code injection) does surface as CVEs in some libraries and frameworks, so A.8.8 finds that minority; the bulk of code injection lives in first-party code (eval(), dynamic code generation in the organization's own application), which A.8.8 does not reach — that is the job of SAST/DAST under A.8.29.