# CVE-2026-56340: vLLM improper input validation in multimodal embeddings

Source: https://junglewise.ai/threats/cve-2026-56340-vllm-improper-input-validation-in-multimodal-embeddings  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-06-20. Updated: 2026-09-25  
License: CC BY 4.0 with a link back

CVE-2026-56340 · Severity: high · CVSS 8.8 · Published 2026-06-20

vLLM is a large language model serving framework that processes embeddings for multimodal AI models. When the prompt-embeds feature is enabled, the system fails to validate tensor indices, allowing attackers to send malformed embedding requests that crash the service or corrupt memory, potentially leading to data breach or arbitrary code execution.

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

## Quick answers

**Is CVE-2026-56340 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-56340 being exploited in the wild.

**How severe is CVE-2026-56340?** High severity, with a CVSS score of 8.8, published 20 June 2026.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0.10.2,fixed=0.13.0.

**Is there a fix for CVE-2026-56340?** Yes. vllm (PyPI): upgrade to 0.13.0 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-56340 attacked?** It is attacked over the network.

**Am I affected by CVE-2026-56340?** Check whether you run vllm (PyPI) 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 0.13.0 or later

  ```sh
  pip install "vllm>=0.13.0"
  ```


## Technical details

The vulnerability stems from missing validation of sparse tensor indices in vLLM's multimodal embedding processor. PyTorch (~v2.0) disables sparse tensor invariant checks by default for performance reasons, so vLLM must explicitly validate that tensor indices are valid, non-negative, and within bounds. An attacker with network access and low privileges can craft embedding requests containing negative or out-of-bounds tensor indices that bypass input validation. When the prompt-embeds feature is enabled, this triggers out-of-bounds write operations (CWE-787/CWE-123), causing crashes (DoS), resource exhaustion, or potentially arbitrary code execution via memory corruption. This is a follow-up to CVE-2025-62164, whose initial fix only disabled the feature by default rather than addressing the root cause. Patches are available in version 0.13.0 and later via PR #30649.

## Affected products

- vllm-project vLLM 0.10.2 to 0.12.x (patched in 0.13.0)

## Identifiers

- CVE-2026-56340
- GHSA-mcmc-2m55-j8jj
- PYSEC-2026-250

## Timeline

- 2026-01-08: disclosed: Published in GitHub Advisory Database
- 2026-01-08: patched: Fixed in vLLM 0.13.0 via PR #30649

## References

- [https://github.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jj](https://github.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jj)
- [https://github.com/vllm-project/vllm/pull/30649](https://github.com/vllm-project/vllm/pull/30649)
- [https://access.redhat.com/security/cve/CVE-2026-56340](https://access.redhat.com/security/cve/CVE-2026-56340)
- [https://bugzilla.redhat.com/show_bug.cgi?id=2491060](https://bugzilla.redhat.com/show_bug.cgi?id=2491060)
- [https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-250.yaml](https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-250.yaml)
- [https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-56340.json](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-56340.json)

## 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)