CVE-2026-73560
vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections
- State
- Published
- Severity
- 6.5 Medium
- Published
- Aug 17, 2026
- Updated
- Aug 18, 2026
- Reserved
- Aug 12, 2026
Description
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mimo_v2_omni.py passes attacker-controlled image and audio strings through _fetch_image, requests.get, and Image.open instead of MediaConnector, bypassing allowed_media_domains and allowed_local_media_path protections and allowing server-side requests and reads of arbitrary files accessible to the vLLM process. This issue is fixed in version 0.26.0.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.1 | 6.5 Medium | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N | GitHub_M |
Weaknesses
- CWE-918 Server-Side Request Forgery (SSRF)
Affected Products
| Product | Versions |
|---|---|
vllmvllm-project |
|
References
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.