CVE-2025-46722 | vLLM has a Weakness in MultiModalHasher Image Hashing Implementation

vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks. This issue has been patched in version 0.9.0.

Published: 2025-05-29 Last update: 2026-06-17 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2025-46722 is rated Low Risk (22.8/100): CVSS Medium severity, with low exploitation likelihood (EPSS 0.26%). Monitor for updates and reassess as exploit intelligence or EPSS changes.

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-2025-46722

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 2026-06-15 0.23% 0.26% +0.03%
2 2026-03-25 0.05% 0.23% +0.18%
3 2025-05-30 — 0.05% —

Full EPSS history (3 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2025-46722

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
4.2 3.1 MEDIUM
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L 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:H)
Even with access, the exploit needs extra luck, timing, or a fussy environment to actually work.
Privileges required (PR:L)
A normal user session is enough; they don’t have to be admin.
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:L)
Some sensitive info could get out, but not a total data dump.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:L)
Might cause slowdowns, glitches, or partial disruption—not a full brick.
 1.6 2.5 [email protected]
7.3 3.1 HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L 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:L)
Some sensitive info could get out, but not a total data dump.
Integrity (I:L)
Attackers could change some data, but it’s limited—not everything goes.
Availability (A:L)
Might cause slowdowns, glitches, or partial disruption—not a full brick.
 3.9 3.4 [email protected]

Weakness enumeration for CVE-2025-46722

GitHub Security Advisory for CVE-2025-46722

GHSA-c65p-x677-fgj6 · Severity: medium · Ecosystem: pip — vLLM has a Weakness in MultiModalHasher Image Hashing Implementation

OS Trackers for CVE-2025-46722

vendor priority summary link
redhat medium — https://access.redhat.com/security/cve/CVE-2025-46722

Affected software / configurations for CVE-2025-46722

Vendor Product Version Raw CPE
vllm vllm >= 0.7.0, < 0.9.0 cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

References for CVE-2025-46722

cvelogic Threat Intelligence