EUVD-2026-75181

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...

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 ...

CVE-2026-87994

Open WebUI versions 0.9.5 through 0.11.1 are affected by an authorization flaw in the channel branch of chat_completion in backend/open_webui/main.py. The endpoint verified channel write access and membership for a supplied message_id but failed to confirm that the calling user was the original a...

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

Summary Xinference 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...

EUVD-2026-64146

Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval in xinference/model/llm/toolparsers/llama3toolparser.py and xinference/model/llm/utils.py. Requests to...

CVE-2026-73557

vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...

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-2026-43628 llama.cpp b3978–b9058 Integer Underflow via DRY Sampler

llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dryallowedlength set to INT32MIN to the /v1/completions or...

CVE-2026-43628 llama.cpp b3978–b9058 Integer Underflow via DRY Sampler

llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dryallowedlength set to INT32MIN to the /v1/completions or...

CVE-2026-70484

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.7.0 until 0.11.0, the legacy chat-completions features block trusted a client-supplied imagegeneration flag and did not re-check the features.imagegeneration permission that the direct image routes and...

Open WebUI: Users denied the image-generation permission can still generate images via chat completions

Summary An authenticated user whose features.imagegeneration permission has been revoked can still make the server generate images by sending the feature flag in a chat-completion request. The chat pipeline took the client-supplied features object at face value and never re-checked the permission...

CVE-2026-70484 Open WebUI: Users denied the image-generation permission can still generate images via chat completions

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.7.0 until 0.11.0, the legacy chat-completions features block trusted a client-supplied imagegeneration flag and did not re-check the features.imagegeneration permission that the direct image routes and...

CVE-2026-70484 Open WebUI: Users denied the image-generation permission can still generate images via chat completions

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.7.0 until 0.11.0, the legacy chat-completions features block trusted a client-supplied imagegeneration flag and did not re-check the features.imagegeneration permission that the direct image routes and...

CVE-2026-70484

Open WebUI vulnerability CVE-2026-70484 affects the self-hosted AI platform Open WebUI in versions 0.7.0 through 0.11.0. The legacy chat-completions features did not re-check the features.image_generation permission enforced on direct image routes and native function-calling paths, allowing an au...

CVE-2026-15974

SGLang (CVE-2026-15974) has a documented SSRF and local file-read flaw in the multimodal generation endpoint /v1/chat/completions caused by unsanitized image_url, enabling access to internal metadata, secrets, and services. The connected sources confirm the vulnerability details but do not provid...

CVE-2026-15974 CVE-2026-15974

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...

PT-2026-66560

Name of the Vulnerable Software and Affected Versions SGLang affected versions not specified Description An SSRF Server-Side Request Forgery and local file read issue exists in the multimodal generation endpoint '/v1/chat/completions'. This occurs because the image url variable is not properly...

Server-side Request Forgery (SSRF)

Overview Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the imageurl parameter in the chat completions endpoint. An attacker can access internal services and cloud metadata endpoints by supplying a crafted URL that redirects to internal addresses, as...

CVE-2026-63764

LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery SSRF vulnerability in the loadhttpurl function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An...

CVE-2026-63764 LMDeploy Server-Side Request Forgery via HTTP Redirect Bypass

LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery SSRF vulnerability in the loadhttpurl function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validating hosts after HTTP redirects. An...