vLLM: Completion prompt lists fan out into unbounded engine requests

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

6.5 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

EPSS

• CVE-2026-73559: 0.58% estimated exploitation activity in the next 30 days; percentile 47.91 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary The /v1/completions request model accepts prompt as a list of text prompts or a list of token-id prompts without any outer prompt-count bound. The serving path turns each element into a separate engine input, creates one engine generator per element, merges all generators, and allocates a response slot per prompt. An authenticated API client can therefore turn one request into an attacker-chosen number of backend subrequests before any aggregate request-count budget is enforced. Technical Details CompletionRequest.prompt allows both list-shaped prompt inputs and scalar prompts: The validator only requires some prompt-like input to be present: The renderer then expands list-shaped prompts as a sequence. prompttoseq() wraps a scalar string or a single token-id list, but returns a list[str] or list[list[int]] unchanged: OnlineRenderer.preprocesscompletion() appends that whole sequence, and the renderer processes every element: Finally, completion serving creates one backend…

Published by the source

13 Aug 2026, 18:40 UTC

Last modified by the source

13 Aug 2026, 18:40 UTC

Source last checked

26 Oct 2026, 13:50 UTC

1. Revision 1 · created · 26 Oct 2026

   Published from ghsa record GHSA-87x5-vmc3-756j

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-73559

Advisory: vLLM: Completion prompt lists fan out into unbounded engine requests
IDs: CVE-2026-73559, GHSA-87x5-vmc3-756j
Record: https://patchnext.com/advisories/cve-2026-73559 (revision 1, source checked 26 Oct 2026, 13:50 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Medium (CVSS 6.5)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: vllm 0.26.0. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI vllm: affected >= 0.19.0, < 0.26.0; fixed in 0.26.0

## Suggested inspection (read-only)
- `python -m pip show vllm`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on vllm.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://github.com/advisories/GHSA-87x5-vmc3-756j (GitHub-reviewed advisory GHSA-87x5-vmc3-756j lists affected ranges: PyPI vllm >=0.19.0 <0.26.0)

Commands are suggestions: review each one before running it.