THREATOPS
THREAT OPS › Threat News › [NVD] CVE-2026-73559 (MEDIUM 6.5) — vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/i

[NVD] CVE-2026-73559 (MEDIUM 6.5) — vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/i

lownvdPublished 2026-08-13

CVE-2026-73559 CVSS: 6.5 MEDIUM Published: 2026-08-13T16:19:05.863

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_co

Indicators of compromise

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-73559