VulnerabilityPublished 29 May 2025

CVE-2025-46722: vllm · Improper Validation of Consistency Within Input

Affects vllmSource CVE Database V5

Not known to be exploited · CVSS 4.2 Medium : upgrade to 0.9.0 when convenient.

Data as of 26 Oct 2026, 14:05 UTC

CVSS 3.1 base score

4.2Medium

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.3% chance of exploitation in 30 days – higher than 26% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 0.9.0

CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:L

Attack Vector: Network
Attack Complexity: High
Privileges Required: Low
User Interaction: None
Scope: Unchanged
Confidentiality: Low
Integrity: None
Availability: Low

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: High: A successful attack depends on conditions beyond the attacker's control. That is, a successful attack cannot be accomplished at will, but requires the attacker to invest in some measurable amount of effort in preparation or execution against the vulnerable component before a successful attack can be expected. For example, a successful attack may require an attacker to: gather knowledge about the environment in which the vulnerable target/component exists; prepare the target environment to improve exploit reliability; or inject themselves into the logical network path between the target and the resource requested by the victim in order to read and/or modify network communications (e.g., a man in the middle attack).
Privileges Required: Low: The attacker is authorized with (i.e., requires) privileges that provide basic user capabilities that could normally affect only settings and files owned by a user. Alternatively, an attacker with Low privileges may have the ability to cause an impact only to non-sensitive resources.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: Low: There is some loss of confidentiality. Access to some restricted information is obtained, but the attacker does not have control over what information is obtained, or the amount or kind of loss is limited. The information disclosure does not cause a direct, serious loss to the impacted component.
Integrity: None: There is no loss of integrity within the impacted component.
Availability: Low: Performance is reduced or there are interruptions in resource availability. Even if repeated exploitation of the vulnerability is possible, the attacker does not have the ability to completely deny service to legitimate users. The resources in the impacted component are either partially available all of the time, or fully available only some of the time, but overall there is no direct, serious consequence to the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 29 May 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade vllm to 0.9.0.

Affected software

Product	Affected	Fixed in
PyPIvllm`pkg:pypi/vllm`Other threats	Affected <0.9.0 >=0.7.0	Fixed in 0.9.0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

European organizations should upgrade vLLM to version 0.9.0 or later, where the vulnerability is patched by incorporating image metadata into the hashing process to prevent collisions. Until upgrade is feasible, organizations should consider disabling or restricting the use of the MultiModalHasher component for image hashing or implement additional validation checks to verify image dimensions and metadata before caching. Employ network segmentation and strict access controls to limit exposure of vLLM services to trusted users and systems only. Monitoring cache hit/miss patterns for anomalies could help detect exploitation attempts. Additionally, organizations should review and audit AI inference pipelines that process images to ensure no sensitive data leakage occurs due to caching errors. Incorporating image hashing libraries with proven collision resistance or cryptographic hashing methods that include metadata can further mitigate risks. Finally, maintain up-to-date vulnerability management processes to promptly apply patches and monitor vendor advisories.

Description

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.

Impact

For European organizations utilizing vLLM versions between 0.7.0 and 0.9.0, this vulnerability could undermine the reliability of image-based caching mechanisms within AI inference workflows. Incorrect cache hits due to hash collisions may lead to serving incorrect or stale data, potentially degrading the quality of AI model outputs or causing erroneous decisions in automated systems. In sensitive environments such as healthcare, finance, or critical infrastructure where LLMs might process multimodal data including images, this could result in data leakage or exposure of confidential information. Although the direct impact on integrity is limited, the risk of data leakage and availability degradation could affect compliance with European data protection regulations like GDPR. Additionally, organizations relying on vLLM for AI services may face operational disruptions or reputational damage if the vulnerability is exploited. However, the vulnerability requires network access and low privileges, which somewhat limits the attack surface. No known exploits are currently reported in the wild, reducing immediate risk but warranting proactive patching.

CWE-1288Improper Validation of Consistency within Input (opens in a new tab)
Base weakness
The product receives a complex input with multiple elements or fields that must be consistent with each other, but it does not validate or incorrectly validates that the input is actually consistent.
Implementation · Input Validation
Assume all input is malicious. Use an "accept known good" input validation strategy, i.e., use a list of acceptable inputs that strictly conform to specifications. Reject any input that does not strictly conform to specifications, or transform it into something that does.
OWASP Cheat Sheets
XML Security (opens in a new tab)
Mass Assignment (opens in a new tab)
OWASP ASVS 4.0.3
V13.3.1 (opens in a new tab)
V5.1.4 (opens in a new tab)
V5.1.3 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).
CWE-1023Incomplete Comparison with Missing Factors (opens in a new tab)
Class weakness
The product performs a comparison between entities that must consider multiple factors or characteristics of each entity, but the comparison does not include one or more of these factors.

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 7 Jul 2025, 22:56 UTC

WeaknessesCWE-1288, CWE-1023

Technical details

References

Community reviews

Related threats