123 matches found
CVE-2026-109227 SGLang through 0.5.21 Memory Exhaustion DoS via Qwen-VL Video Preprocessing
SGLang through 0.5.21 contains an unbounded memory allocation vulnerability in preprocessvideo in qwenvl.py that decodes frames at full source resolution before applying maxpixels limits. Remote attackers can submit high-resolution videos to /v1/chat/completions on Qwen-VL deployments, and...
EUVD-2026-97433
SGLang through 0.5.21 contains an unbounded memory allocation vulnerability in preprocessvideo in qwenvl.py that decodes frames at full source resolution before applying maxpixels limits. Remote attackers can submit high-resolution videos to /v1/chat/completions on Qwen-VL deployments, and...
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...
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...
Open WebUI: Channel members can overwrite another member's message via the chat completions endpoint
SummaryAny member of a channel who can post to it could also replace the text of a message written by a different member. The channel branch of the chat completions endpoint checked that the caller may write to the channel, and that the targeted message belongs to that channel, but never checked...
Open WebUI: Any authenticated user can inject chats into another user's folder via chat completions
SummaryThe chat-completions endpoint reads a folder id out of the request body and saves the newly created chat into that folder without checking that the caller is allowed to write there. Any authenticated user who knows a folder's id can put a chat of their own into another user's folder,...
PYSEC-2026-4122 Open WebUI: Channel members can overwrite another member's message via the chat completions endpoint
Summary Any member of a channel who can post to it could also replace the text of a message written by a different member. The channel branch of the chat completions endpoint checked that the caller may write to the channel, and that the targeted message belongs to that channel, but never checked...
PYSEC-2026-4118 Open WebUI: Any authenticated user can inject chats into another user's folder via chat completions
Summary The chat-completions endpoint reads a folder id out of the request body and saves the newly created chat into that folder without checking that the caller is allowed to write there. Any authenticated user who knows a folder's id can put a chat of their own into another user's folder,...
PT-2026-105871
Summary Any member of a channel who can post to it could also replace the text of a message written by a different member. The channel branch of the chat completions endpoint checked that the caller may write to the channel, and that the targeted message belongs to that channel, but never checked...
PT-2026-105867
Summary The chat-completions endpoint reads a folder id out of the request body and saves the newly created chat into that folder without checking that the caller is allowed to write there. Any authenticated user who knows a folder's id can put a chat of their own into another user's folder,...
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-2026-99321
Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.29.1 Description The server fetches and fully materializes remote or inline media before enforcing media controls, such as the VLLM MAX AUDIO CLIP FILESIZE MB size cap and the --limit-mm-per-prompt item limits. This...
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...
CVE-2026-57173
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...
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 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...
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...