CVE-2026-73559: vLLM: Completion prompt lists fan out into unbounded engine requests
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.
References
- github.com/advisories/GHSA-87x5-vmc3-756j
- github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e
- github.com/vllm-project/vllm/pull/47845
- github.com/vllm-project/vllm/releases/tag/v0.26.0
- github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
- nvd.nist.gov/vuln/detail/CVE-2026-73559
Code Behaviors & Features
Detect and mitigate CVE-2026-73559 with GitLab Dependency Scanning
Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →