# CVE-2026-73560: vLLM SSRF and arbitrary file read in MiMoV2OmniMultiModalProcessor

Source: https://junglewise.ai/threats/cve-2026-73560-vllm-ssrf-and-arbitrary-file-read-in  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-08-17. Updated: 2026-09-25  
License: CC BY 4.0 with a link back

CVE-2026-73560 · Severity: medium · CVSS 6.5 · Published 2026-08-17

vLLM's MiMoV2OmniMultiModalProcessor lacks SSRF and path validation when loading images or audio from user-supplied URLs and local file paths. An attacker who can control multi_modal_data input can probe internal networks (including cloud metadata services), read local files readable by the vLLM process (e.g., AWS credentials), and generate traffic from the server. This bypasses protections already implemented elsewhere in the codebase.

Technologies: [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm), [Vllm](https://junglewise.ai/threats/technologies/vllm). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi), [Vllm](https://junglewise.ai/threats/vendors/vllm).

## Quick answers

**Is CVE-2026-73560 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-73560 being exploited in the wild.

**How severe is CVE-2026-73560?** Medium severity, with a CVSS score of 6.5, published 17 August 2026.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0,fixed=0.26.0.

**Is there a fix for CVE-2026-73560?** Yes. vllm (PyPI): upgrade to 0.26.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-73560 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-73560?** Check whether you run vllm (PyPI) or Vllm at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## How to fix

- vllm (PyPI): upgrade to 0.26.0 or later

  ```sh
  pip install "vllm>=0.26.0"
  ```


## Technical details

The vulnerability exists in vllm/transformers_utils/processors/mimo_v2_omni.py in the _fetch_image function (lines 231–249) and audio loader (line ~471). These functions call requests.get() directly on HTTP(S) URLs without allowlist validation or Image.open() on file:// paths without path restrictions, bypassing the SSRF and allowed_local_media_path checks in MediaConnector that were previously hardened in CVE-2026-46517, CVE-2026-46518, and related advisories. The vulnerable code is reachable via LLM.generate(multi_modal_data={"image": "http://..."}) and similar batch/library paths. An attacker with control over multi_modal_data can read AWS/GCP/Azure metadata endpoints, probe internal services on 127.0.0.1 or private networks, exfiltrate data via timing oracles, read /etc/passwd or ~/.aws/credentials via file://, or exhaust server resources by hammering arbitrary URLs. The remediation is to route image and audio fetching through MediaConnector.fetch_image/fetch_audio_async, which applies URL allowlists, network-target allowlists, size caps, and local-path allowlists already implemented in earlier patches.

## Affected products

- vLLM Project vLLM < 0.26.0

## Identifiers

- CVE-2026-73560
- GHSA-4hhp-h66f-j5j7
- PYSEC-2026-3934

## Timeline

- 2026-09-08: disclosed
- 2026-09-08: patched: Fixed in vLLM 0.26.0

## References

- [https://api.github.com/users/ibondarenko1](https://api.github.com/users/ibondarenko1)
- [https://github.com/ibondarenko1](https://github.com/ibondarenko1)
- [https://api.github.com/users/ibondarenko1/gists%7B/gist_id%7D](https://api.github.com/users/ibondarenko1/gists%7B/gist_id%7D)
- [https://api.github.com/users/ibondarenko1/repos](https://api.github.com/users/ibondarenko1/repos)
- [https://avatars.githubusercontent.com/u/229061622?v=4](https://avatars.githubusercontent.com/u/229061622?v=4)
- [https://api.github.com/users/ibondarenko1/events%7B/privacy%7D](https://api.github.com/users/ibondarenko1/events%7B/privacy%7D)

## Related threats

- [vLLM chat template resource exhaustion DoS](https://junglewise.ai/threats/cve-2026-115918-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server](https://junglewise.ai/threats/cve-2026-115917-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM off-by-one error in tokenizer max_token_id validation](https://junglewise.ai/threats/cve-2026-115916-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM image format validation bypass in media processing](https://junglewise.ai/threats/cve-2026-115915-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM denial of service in DeepSeek-OCR image processing](https://junglewise.ai/threats/cve-2026-115914-vllm-is-an-inference-and-serving-engine-for-large-language)