Lucene search
+L

97 matches found

OSV
OSV
•added 2026/09/16 10:12 p.m.•10 views

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...

6.5CVSS6AI score0.00687EPSS
SaveExploits0References6
OSV
OSV
•added 2026/09/16 4:34 p.m.•7 views

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...

6.5CVSS5.9AI score
SaveExploits0References6
CVE
CVE
•added 2026/09/16 4:34 p.m.•15 views

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 ...

6.5CVSS5.9AI score0.00687EPSS
SaveExploits0References4
EUVD
EUVD
•added 2026/09/16 4:34 p.m.•11 views

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...

6.5CVSS5.9AI score0.00687EPSS
SaveExploits0References4
Cvelist
Cvelist
•added 2026/09/16 4:34 p.m.•37 views

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...

6.5CVSS0.00687EPSS
SaveExploits0References4
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/16 12:00 a.m.•1 views

CVE-2026-69147: Uncontrolled Resource Consumption

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 mediaiokwargs.video.videobackend to pynvvideocodec, and MediaConnector.fetchvideo forwards that choice to VideoMediaIO even when startup configuration...

6.5CVSS5.8AI score0.00548EPSS
SaveExploits0References3
NVD
NVD
•added 2026/09/15 5:16 a.m.•20 views

CVE-2026-90878

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...

5.3CVSS0.00533EPSS
SaveExploits0References7
Vulnrichment
Vulnrichment
•added 2026/09/15 4:15 a.m.•9 views

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...

5.3CVSS5AI score0.00533EPSS
SaveExploits0References7
EUVD
EUVD
•added 2026/09/15 4:15 a.m.•13 views

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...

5.3CVSS5AI score0.00533EPSS
SaveExploits0References7
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/15 12:00 a.m.•0 views

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...

5.3CVSS5.2AI score0.00533EPSS
SaveExploits0References3
Github Security Blog
Github Security Blog
•added 2026/09/10 3:10 p.m.•16 views

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...

4.3CVSS5.7AI score0.00372EPSS
SaveExploits1References6Affected Software1
OSV
OSV
•added 2026/09/10 3:10 p.m.•6 views

GHSA-FMQH-XP37-5HR8 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...

4.3CVSS5.7AI score0.00372EPSS
SaveExploits1References6
EUVD
EUVD
•added 2026/09/10 3:10 p.m.•8 views

EUVD-2026-75181

Open WebUI: Any authenticated user can inject chats into another user's folder via chat completions...

4.3CVSS5.7AI score0.00372EPSS
SaveExploits1References5
Github Security Blog
Github Security Blog
•added 2026/09/10 3:10 p.m.•14 views

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,...

4.3CVSS5.8AI score0.00372EPSS
SaveExploits1References6Affected Software1
OSV
OSV
•added 2026/09/10 3:10 p.m.•7 views

GHSA-3PF7-Q2G3-WJ28 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,...

4.3CVSS5.8AI score0.00372EPSS
SaveExploits1References6
PyPA
PyPA
•added 2026/09/10 9:44 a.m.•7 views

Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing

SummaryXinference used Python's unsafe eval function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to...

10CVSS6.4AI score0.01226EPSS
SaveExploits0References8Affected Software1
NVD
NVD
•added 2026/09/09 10:18 p.m.•9 views

CVE-2026-87997

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...

4.3CVSS0.00372EPSS
SaveExploits1References4
CVE
CVE
•added 2026/09/09 9:30 p.m.•21 views

CVE-2026-87997

Open WebUI (self-hosted AI platform) versions 0.10.0 through 0.11.1 contain an access-control bypass in POST /api/chat/completions and POST /api/v1/chat/completions (backend/open_webui/main.py). A client-supplied folder_id was copied into a new chat without the folder write-access check enforced ...

4.3CVSS5.7AI score0.00372EPSS
SaveExploits1References4Affected Software1
Cvelist
Cvelist
•added 2026/09/09 9:30 p.m.•40 views

CVE-2026-87997 Open WebUI: Any authenticated user can inject chats into another user's folder via chat completions

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...

4.3CVSS0.00372EPSS
SaveExploits1References4
OSV
OSV
•added 2026/09/09 9:30 p.m.•13 views

CVE-2026-87997 Open WebUI: Any authenticated user can inject chats into another user's folder via chat completions

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...

4.3CVSS5.8AI score
SaveExploits0References6
Rows per page
Query Builder