ZDF
Sign inSign up

Vulnerabilities

Vulnerability · CVE-2025-46722

vLLM is an inference and serving engine for large language models (LLMs).

Published May 29, 2025 · catalog updated May 29, 2025 · vLLM is an inference

Check this week

CVE-2025-46722 is not in CISA KEV. FIRST estimates a 32.00% chance of exploitation in the next 30 days. Check whether you run vLLM is an inference.

Gaps on this record

  • The stored product name is a package slug. The name on this page is taken from the title (vLLM is an inference).
  • No vendor fix or required action is stored. Compare the linked advisory before you change production.
Severity
Medium4.2
Known exploitation
Not in CISA/VulnCheck KEV
EPSS
32.00%
Remediation
Version ranges on file
Affected products
vendor vllm-project vllm 0.7.0, < 0.9.0

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

Are you affected?

Enter the version you run. The result uses only the ranges stored on this record.

The check returns affected, not affected, or incomplete. It does not guess a version that is missing from the record.

  • vendor vllm-project vllm 0.7.0, < 0.9.00.7.0, < 0.9.0

How to fix CVE-2025-46722

What to do

Three questions, each answered from this record only. Confirm the vendor advisory before you patch.

Should you patch?

CVE-2025-46722 is not in CISA KEV. FIRST estimates a 32.00% chance of exploitation in the next 30 days. Check whether you run vLLM is an inference.

Which versions are affected?

Compare what you have installed with vllm-project vllm 0.7.0, < 0.9.0 0.7.0, < 0.9.0. Compare the installed version with the linked vendor advisory before you change production.

What should an analyst verify?

No weakness class is stored. EPSS 32.00%. There is no CISA KEV listing. No Exploit-DB or Metasploit reference is linked. Use the source links for the original advisory.

Code

The project this record applies to. Exploit listings stay in References.

Timeline

Detection, updates, and resolution for this record.

  1. May 29, 2025 · EUVD

    Detected

    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 s

  2. May 29, 2025 · EUVD

    Updated

    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 s

Sources

  • CVE.orgVulnerability recordCVE-2025-46722

    Official CVE identifier

    cve.org
  • EUVDVulnerability recordEUVD-2025-16188

    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 serializ

    euvd.enisa.europa.eu

References

Freshness

Last verified in this catalog May 29, 2025. Significant claims (KEV, EPSS, CVSS, affected ranges) come from the source rows above — open the original publisher for the authoritative advisory.