Cyber Resilience

CVE-2026-22778

Info Disclosure in Vllm 0.8.3 – 0.14.1

Published
02 February 2026
Modified
15 July 2026
Patch / advisory
CVSS Score v3.1 9.8
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS Score 0.037 89th percentile
Risk Priority 77 floored blend · peak EPSS

Summary

CVE-2026-22778 is a critical-severity Insertion of Sensitive Information into Log File (CWE-532) vulnerability in Vllm Vllm. Its CVSS base score is 9.8 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Unsecured Credentials (T1552); ranked in the top 11% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as NLP and Transformers; in the Privacy and Disclosure risk domain.

The strongest mitigations our analysis identified map to SI-11 (Error Handling) — see the control section below for these in your framework.

Deeper analysis AI-assisted summary

Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.

CVE-2026-22778 is a heap address disclosure vulnerability (CWE-532) in vLLM, an open-source inference and serving engine for large language models (LLMs). The issue affects versions from 0.8.3 up to but not including 0.14.1. Specifically, when an invalid image is submitted to vLLM's multimodal endpoint, the Python Imaging Library (PIL) generates an error that vLLM echoes back to the client, inadvertently leaking a heap memory address. This disclosure has a CVSS v3.1 base score of 9.8 (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H), reflecting its critical severity.

Unauthenticated remote attackers with network access to a vulnerable vLLM instance can exploit this by sending a crafted invalid image to the multimodal endpoint, obtaining a heap address leak that significantly weakens Address Space Layout Randomization (ASLR), reducing brute-force guesses from approximately 4 billion to around 8. This information disclosure can be chained with a separate heap overflow vulnerability in the JPEG2000 decoder implemented via OpenCV or FFmpeg, enabling full remote code execution (RCE) on the server.

The vulnerability is addressed in vLLM version 0.14.1, as detailed in the project's security advisory (GHSA-4r2x-xpjr-7cvv) and associated pull requests (#31987 and #32319). Security practitioners should upgrade to 0.14.1 or later and review exposure of multimodal endpoints, particularly in LLM serving environments. The release notes for v0.14.1 confirm the fix.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a…

more

heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Privacy and Disclosure
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: llms, opencv, vllm

Related Threats

MITRE ATT&CK Enterprise Techniques

T1552 Unsecured Credentials Credential Access
Adversaries may search compromised systems to find and obtain insecurely stored credentials.
T1552.001 Credentials In Files Credential Access
Adversaries may search local file systems and remote file shares for files containing insecurely stored credentials.
T1592.002 Software Reconnaissance
Adversaries may gather information about the victim's host software that can be used during targeting.
T1005 Data from Local System Collection
Adversaries may search local system sources, such as file systems, configuration files, local databases, virtual machine files, or process memory, to find files of interest and sensitive data prior to Exfiltration.
T1082 System Information Discovery Discovery
An adversary may attempt to get detailed information about the operating system and hardware, including version, patches, hotfixes, service packs, and architecture.
T1592 Gather Victim Host Information Reconnaissance
Adversaries may gather information about the victim's hosts that can be used during targeting.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2026-54236Same product: Vllm Vllm
CVE-2026-7141Same product: Vllm Vllm
CVE-2025-46570Same product: Vllm Vllm
CVE-2024-11041Same product: Vllm Vllm
CVE-2026-34755Same product: Vllm Vllm
CVE-2025-30202Same product: Vllm Vllm
CVE-2026-34760Same product: Vllm Vllm
CVE-2025-46560Same product: Vllm Vllm
CVE-2025-29770Same product: Vllm Vllm
CVE-2025-48942Same product: Vllm Vllm

Affected Assets

vllm
vllm
0.8.3 — 0.14.1

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)

Validate
Prove the fix (OWASP ASVS)
  • V16.5.1

Mitigating Controls (NIST 800-53 r5) AI

si-11 directly requires error messages to avoid revealing exploitable information about the system or its data.

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.

PR.PS-06 mostly match
prevents

Secure SDLC practices directly prohibit writing sensitive data to logs; eliminating the weakness satisfies only one narrow slice of the control.

PR.PS-04 partial match
prevents

Log generation configuration can and should exclude sensitive data, but the control statement focuses on availability rather than content filtering.

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.

A.8.15 Logging mostly match
prevents

Requiring de-identification and privacy controls before logs leave the organization reduces the chance that sensitive data inadvertently captured in logs becomes exposed to external parties.

prevents

Secure coding standards explicitly forbid exposing sensitive data in errors.

finds

Security testing can detect error messages that leak sensitive information.

mitigates

By defining what records must be kept, where, and for how long, the control discourages the inadvertent inclusion of sensitive information in logs or other externally accessible files that fall outside the formal record system.

mitigates

Mandating deletion of temporary files and logs that may contain sensitive information prevents those artifacts from remaining accessible after the data is no longer needed.

A.8.11 Data masking partial match
mitigates

When log entries are produced from masked data sets, the control prevents the inadvertent insertion of sensitive values into externally accessible log files.

References