CVE-2026-22773Medium· 6.5▾ SunlitvLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a s…
▾ Sunlit zone — Low / medium · no exploitation signal
impact 35.8 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Stakeholder-Specific Vulnerability Categorization from CISA's ADP record at CVE.org: whether exploitation is observed, whether an attack can be automated, and how much of the system is at stake.
Exploit-prediction probability, daily snapshots since Sep 12.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
Last analysed / modified upstream
0.4%
vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination. This issue has been patched in version 0.12.0.
vllm >= 0.6.4, < 0.12.0Upgrade past the affected range:
vllm 0.12.0Connected 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-2026-115918Medium· 6.5vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs
CVE-2026-116179High· 7.5vLLM 0.18.0 before 0.31.0 Memory Exhaustion via media_io_kwargs num_frames Override
CVE-2026-114055High· 7.5vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs
CVE-2026-105760Medium· 5.3vLLM is an inference and serving engine for large language models