CVE-2026-115918Medium· 6.5▾ SunlitvLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when n…
▾ Sunlit zone — Low / medium · no exploitation signal
impact 35.8 · likelihood 0 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.
vllm >= 0.16.0, < 0.32.0Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-115911Medium· 6.5vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool
CVE-2026-115913Medium· 6.5vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine
CVE-2026-114055High· 7.5vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs
CVE-2026-105759Medium· 5.9vLLM is an inference and serving engine for large language models
CVE-2026-105760Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-100648Medium· 5.3vllm before 0.29.0 fails to enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit in multimodal chat audio decoding, allowing unauthenticated clients to bypass file size restrictions