AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

GHSA-87x5-vmc3-756j: vLLM: Completion prompt lists fan out into unbounded engine requests

OSV AI package advisories · observation · Aug 13, 2026 · UTC

## 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 prom

Read original source ↗ Open in workspace

recordType
vulnerability
status
active
evidenceStatus
reported
region
Global

Evidence & attribution

First collected: 2026-09-20T22:31:48.298Z. This is not the publication date.