CVE-2026-22778 | vLLM leaks a heap address when PIL throws an error

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 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.

Published: 2026-02-02 Last update: 2026-02-23 Assigner: [email protected] Source: [email protected]

Conclusion & alert: CVE-2026-22778 is rated Moderate Risk (45.8/100): CVSS Critical severity, with low exploitation likelihood (EPSS 0.06%). Mandatory action: Review affected assets and schedule remediation.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2026-22778

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-02-03 0.06%

Full EPSS history (1 record total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-22778

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
9.8 3.1 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
3.9 5.9 [email protected]

Weakness enumeration for CVE-2026-22778

GitHub Security Advisory for CVE-2026-22778

GHSA-4r2x-xpjr-7cvv · Severity: critical · Ecosystem: pip — vLLM has RCE In Video Processing

OS Trackers for CVE-2026-22778

vendor priority summary link
redhat critical https://access.redhat.com/security/cve/CVE-2026-22778

Affected software / configurations for CVE-2026-22778

Vendor Product Version Raw CPE
vllm vllm >= 0.8.3, < 0.14.1 cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

References for CVE-2026-22778

cvelogic Threat Intelligence