vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool

影響: pip:vllm >= 0.19.0, < 0.32.0 → 0.32.0

vLLM renders chat templates by passing the resolved Jinja2 source to tokenizer.apply_chat_template(), which compiles and .render()s it in an ImmutableSandboxedEnvironment. The sandbox prevents code-execution escapes but imposes no wall-clock timeout, no output-size cap, and no nested-loop or binop limit. The render runs in a ThreadPoolExecutor whose max_workers defaults to 1, and CPython worker threads cannot be interrupted. An authenticated API client (or a malicious model repo loaded with tru…

Read on GitHub Advisory Database

On 10/29/2026, 06:14 AM, GitHub Advisory Database published "vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool" (type: Advisory). Severity is "Medium" (medium). Related technologies: Python. CVE: CVE-2026-115911.