vllm: Incomplete Comparison with Missing Factors
CVE-2025-46722 is a high-severity incomplete comparison with missing factors vulnerability in vllm from Vllm-project, with a CVSS 3.1 base score of 7.3 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, without any action from a user. Affected vllm versions: >= 0.7.0, < 0.9.0. The record does not name a fixed version, so check the vendor advisory. There is no confirmed exploitation so far. EPSS estimates a 0.34% chance of exploitation within 30 days, which is low compared with other CVEs.
High severity with no evidence of exploitation so far.
What to do
- Check which version of vllm you run against the affected versions below, and install the vendor's latest release.
- Read the advisory on github.com for workarounds and exact fixed builds.
- Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.
Affected products and versions
| Vendor | Product | Affected versions | Fixed in |
|---|---|---|---|
| Vllm-project | vllm | >= 0.7.0, < 0.9.0 | Not stated |
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- NetworkCan be exploited remotely over a network, including the internet.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- NoneNo account or login is needed.
- User interaction
- NoneNo action by a victim is required.
- Scope
- UnchangedImpact stays within the vulnerable component.
- Confidentiality
- LowSome restricted data can be read.
- Integrity
- LowLimited modification of data is possible.
- Availability
- LowPerformance or availability is reduced.
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L. Scored by NVD.
| Scoring system | Score | Severity | Scored by |
|---|---|---|---|
| CVSS 3.1 | 4.2 | Medium | CNA (github.com) |
| CVSS 3.1 | 7.3 | High | NVD |
Official 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.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Incomplete Comparison with Missing Factors
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.
More Incomplete Comparison with Missing Factors vulnerabilities (CWE-1023)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: none, automatable: no, technical impact: partial).
- Record last changed materially (score, affected products, status or references).
References
Patches and release notes
Other vulnerabilities in vllm
- 7.5 High severity
- 9.8 Critical severity
- 8.8 High severity
- 7.7 High severity
- 7.5 High severity
- 7.5 High severity
Spotted an error? Tell us.