Vulnerability in vllm (CVE-2025-46722)
Summary
Vulnerability in vllm (CVE-2025-46722). Risk of unauthorized operations or information disclosure. Exploitable via MultiModalHasher. Mitigation: upgrade to 0.9.0 or later.
Original description
The description as published by the source.
Summary
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.
Details
- Affected file:
vllm/multimodal/hasher.py - Affected method:
MultiModalHasher.serialize_item
https://github.com/vllm-project/vllm/blob/9420a1fc30af1a632bbc2c66eb8668f3af41f026/vllm/multimodal/hasher.py#L34-L35 - Current behavior: For
Image.Imageinstances, onlyobj.tobytes()is used for hashing. - Problem description:
obj.tobytes()does not include the image’s width, height, or mode metadata. - Impact: Two images with the same pixel byte sequence but different sizes could be regarded as the same image by the cache and hashing system, which may result in:
- Incorrect cache hits, leading to abnormal responses
- Deliberate construction of images with different meanings but the same hash value
Recommendation
In the serialize_item method, serialization of Image.Image objects should include not only pixel data, but also all critical metadata—such a…
Source: OSV.dev (Open Source Vulnerabilities) NVD GitHub Advisory OSV
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2025-46722 has been found in vllm.
Attackers can target a specific entry point like MultiModalHasher over the network to misuse the product.
Risk of unauthorized operations or information disclosure.
What to do: upgrade vllm to 0.9.0 or later.
If unsure, ask your IT team or search "vllm CVE-2025-46722" on the vendor's site.
CVE-2025-46722 (vllm) — CWE-1023
Attack vector: remote (network-reachable) / no user interaction
Attack surface: MultiModalHasher / PIL.Image.Image / MultiModalHasher.serialize_item / Image.Image
Patched: 0.9.0 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
A vulnerability (CWE-1023) exists in vllm. Attackers reach the vulnerable code path via MultiModalHasher.
Check the vendor advisory for the affected versions of vllm. Attack surface: MultiModalHasher / PIL.Image.Image / MultiModalHasher.serialize_item / Image.Image.
Severity: ?. Risk of unauthorized operations or information disclosure.
Update to 0.9.0.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'vllm' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'vllm' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
vllmを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply patch patch
Upgrade vllm to 0.9.0ステージング環境で 0.9.0 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。
-
3Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
Affected packages
References
- advisory nvd.nist.gov
- package github.com
- web github.com
- web github.com
- web github.com
- web github.com