PYSEC-2026-4179 vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

Summary The audio decode-duration guard maxdurations, env VLLMMAXAUDIODECODEDURATIONS, default 600s that protects against audio decompression-bomb DoS is wired into only the speech-to-text path /v1/audio/transcriptions. The chat audio path /v1/chat/completions, inputaudio content parts calls the...

vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

SummaryThe audio decode-duration guard maxdurations, env VLLMMAXAUDIODECODEDURATIONS, default 600s that protects against audio decompression-bomb DoS is wired into only the speech-to-text path /v1/audio/transcriptions. The chat audio path /v1/chat/completions, inputaudio content parts calls the...

CVE-2026-100654

vLLM before 0.29.0 accepts user-controlled stoptokenids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When mintokens 0, the stop token ids a...

PT-2026-99325

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.29.0 Description The software fails to validate if the values provided in stop token ids are within the model vocabulary or logits range, checking only that they are integers. When min tokens is greater than 0, these I...

GHSA-HCWQ-8WJF-3GCR vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

Summary The audio decode-duration guard maxdurations, env VLLMMAXAUDIODECODEDURATIONS, default 600s that protects against audio decompression-bomb DoS is wired into only the speech-to-text path /v1/audio/transcriptions. The chat audio path /v1/chat/completions, inputaudio content parts calls the...

EUVD-2026-80880

vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the inputaudio handling path for /v1/chat/completions calls AudioMediaIO.loadbytes or AudioMediaIO.loadfile without passing VLLMMAXAUDIODECODEDURATIONS to the shared audio decoder. An unauthenticated client can...

CVE-2026-57173 vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the inputaudio handling path for /v1/chat/completions calls AudioMediaIO.loadbytes or AudioMediaIO.loadfile without passing VLLMMAXAUDIODECODEDURATIONS to the shared audio decoder. An unauthenticated client can...

CVE-2026-57173

vLLM versions prior to 0.24.0 contain an audio decompression-bomb denial-of-service in the input_audio handling path for /v1/chat/completions. The root cause is that AudioMediaIO.load_bytes and AudioMediaIO.load_file are called without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio ...

CVE-2026-57173 vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the inputaudio handling path for /v1/chat/completions calls AudioMediaIO.loadbytes or AudioMediaIO.loadfile without passing VLLMMAXAUDIODECODEDURATIONS to the shared audio decoder. An unauthenticated client can...

PT-2026-93837

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.24.0 Description An issue exists in the audio handling path for the /v1/chat/completions endpoint where the input audio content is processed without a duration limit. Specifically, the AudioMediaIO.load bytes and...

CVE-2026-90878 vllm-project vLLM Jinja Template Rendering completions resource consumption

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 chattemplate causes resource consumption. The attack can be initiated remotely. The exploit...

EUVD-2026-78268

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 chattemplate causes resource consumption. The attack can be initiated remotely. The exploit...

CVE-2026-90878: Uncontrolled Resource Consumption

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 chattemplate causes resource consumption. The attack can be initiated remotely. The exploit...

CVE-2026-87997: Authorization Bypass Through User-Controlled Key

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.10.0 until 0.11.1, POST /api/chat/completions and POST /api/v1/chat/completions in backend/openwebui/main.py copied a client-supplied folderid into a new chat without applying the folder write-access chec...

PT-2026-71672

Name of the Vulnerable Software and Affected Versions vLLM versions 0.20.2rc0 through 0.25.x Description A race condition exists in the safe load prompt embeds function within vllm/renderers/embed utils.py when enable prompt embeds is enabled. The issue occurs because torch.sparse.check sparse...

CVE-2026-15974: Server-Side Request Forgery (SSRF)

SGLang contains an SSRF and local file read in the multimodal generation endpoint /v1/chat/completions due to unsanitized imageurl, allowing access to internal metadata, secrets, and services...

CVE-2025-62426: Allocation of Resources Without Limits or Throttling

vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the...

CVE-2025-48944

vLLM is an inference and serving engine for large language models LLMs. In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality ...

CVE-2025-48944: Improper Input Validation

vLLM is an inference and serving engine for large language models LLMs. In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality ...