Threat Intelligence Database

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions and Responses can set media_io_kwargs.video.video_backend to pynvvideocodec, and MediaConnector.fetch_video forwards that choice to VideoMediaIO even when startup configuration selected a software decoder. The engine's _reserve_mm_ipc_gpu_memory logic budgets decoder memory only from static configuration, so the request-selected VIDEO_LOADER_REGISTRY backend can create a CUDA context, decoder surfaces, and decoded-frame allocations that were not removed from the engine's KV-cache budget. An attacker able to submit video requests to a video-capable GPU deployment with PyNvVideoCodec installed can exhaust shared GPU memory, causing request failures, worker crashes, or denial of service. The first release containing the fix is version 0.28.0.

vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM allocation, bypassing the duration guard already used by /v1/audio/transcriptions and causing an out-of-memory worker crash. Inline data URLs reach this path without being bounded by VLLM_AUDIO_FETCH_TIMEOUT. The issue affects deployments serving an audio-capable model, and authentication changes only the deployment-specific reachability. This issue is fixed in version 0.24.0.

A vulnerability was found in vllm-project vllm up to 0.29.0. Affected by this issue is some unknown functionality of the file vllm/v1/sample/thinking_budget_state.py. The manipulation results in inefficient algorithmic complexity. It is possible to launch the attack remotely. The pull request to fix this issue awaits acceptance.

A vulnerability was found in vllm-project vLLM 0.26.0/0.27.0. Affected is the function MoRIIOConnectorScheduler.request_finished/MoRIIOConnectorWorker.get_finished/MoRIIOWrapper._handle_release_message of the file vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_connector.py of the component MoRIIO Acknowledgement Handler. Performing a manipulation of the argument request_id/kv_transfer_params results in resource consumption. It is possible to initiate the attack remotely. The project was informed of the problem early through a pull request but has not reacted yet.

A vulnerability was determined in vllm-project vLLM up to 0.27.1. This affects an unknown part of the file /v1/chat/completions of the component Jinja Template Rendering. This manipulation of the argument chat_template causes resource consumption. The attack can be initiated remotely. The exploit has been publicly disclosed and may be utilized. The pull request to fix this issue awaits acceptance.

vLLM versions >=0.10.2 and <0.28.0 do not apply any audio decode-size or duration limit when extracting audio from video input for NanoNemotronVL models. In nano_nemotron_vl.py, _extract_audio_from_videos calls load_audio_pyav(BytesIO(video_bytes)) without the max_duration_s or max_decode_bytes parameters, so neither VLLM_MAX_AUDIO_DECODE_DURATION_S nor VLLM_MAX_AUDIO_DECODE_BYTES is enforced (unlike the direct audio upload path in AudioMediaIO). When a NanoNemotronVL model is served with use_audio_in_video=True, an attacker who supplies a small, highly compressed video as multimodal input can force the server to allocate gigabytes of memory during audio decoding, resulting in a denial of service. Fixed in vLLM 0.28.0.

vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.

CVE-2026-73557 is a race condition vulnerability in the vllm-project's vllm software affecting versions from 0.20.2rc0 up to but not including 0.26.0. It arises from improper synchronization of a process-global sparse tensor invariant guard in PyTorch 2.11.0 during concurrent prompt-embedding reconstruction within a single chat completion request. This can lead to invalid sparse tensor deserialization and subsequent unsafe dense tensor conversion. The vulnerability requires the --enable-prompt-embeds feature (default off) but does not require multiple workers or multimodal embeddings. The flaw allows a malicious payload to bypass the follow-up guard, potentially causing memory corruption or denial of service as documented in the related CVE-2025-62164. The CVSS 4.0 base score is 6.3 (medium severity).

CVE-2026-71486 is a medium severity vulnerability in vllm-project vllm versions prior to 0.26.0. It affects the /v1/completions/derender and /v1/chat/completions/derender API endpoints, which accept client-supplied generated output data without enforcing limits on token counts or response sizes. This allows an authenticated API client to cause uncontrolled CPU and memory consumption proportional to the size of the attacker-supplied token data, bypassing normal generation output bounds.

A Server-Side Request Forgery (SSRF) vulnerability exists in vllm-project's vllm prior to version 0.26.0. The MiMoV2OmniMultiModalProcessor improperly handles attacker-controlled image and audio inputs by bypassing domain and local path restrictions, allowing unauthorized server-side requests and file reads accessible to the vLLM process. This vulnerability is fixed in version 0.26.0.