Quantum Secular Labs / Blog / Advisories

CVE-2026-115915: Vllm: Command injection

CVE-2026-115915 is rated critical with a CVSS v3.1 base score of 9.8 and affects Vllm. Per its scoring, it can be exploited over the network, without authentication, without any user interaction. The scored impact on confidentiality, integrity and availability is the highest available.

Vulnerability description

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through Image.open(BytesIO(data)) without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request paths through parse_image() and fetch_image() can therefore dispatch an EPS payload to host components. A host with Ghostscript affected by CVE-2024-29510 can execute commands with the vLLM process's privileges, while environments using Pillow 12.0.0 through 12.2.0 can trigger CVE-2026-59203 and exhaust media-loading workers. Deployments without the applicable vulnerable dependency are not affected by that corresponding impact. This issue is fixed in version 0.32.0.

Severity breakdown

CVSS v3.1 9.8: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

• Attack vector: Network. Exploitable remotely over the network, with no need for local or physical access.
• Attack complexity: Low. No special conditions; the attack can be repeated reliably.
• Privileges required: None. No account or prior access is needed.
• User interaction: None. No action from any user is needed.
• Scope: Unchanged. Impact stays within the vulnerable component.
• Confidentiality impact: High. Total loss of confidentiality; sensitive data can be fully disclosed.
• Integrity impact: High. Total loss of integrity; data or system state can be fully modified.
• Availability impact: High. Total loss of availability; the component can be shut down.

Underlying weakness

CWE-20: Improper Input Validation

The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.

CWE-183: Permissive List of Allowed Inputs

The product implements a protection mechanism that relies on a list of inputs (or properties of inputs) that are explicitly allowed by policy because the inputs are assumed to be safe, but the list is too permissive - that is, it allows an input that is unsafe, leading to resultant weaknesses.

Affected products

• Vllm: from 0.30.0 before 0.32.0

References

• https://github.com/vllm-project/vllm/commit/710ac56e691d4713feca50a43e6c440f07d373fd
• https://github.com/vllm-project/vllm/pull/60022
• https://github.com/vllm-project/vllm/security/advisories/GHSA-h3rc-j82p-2c3h
• https://github.com/vllm-project/vllm/releases/tag/v0.32.0