CVE-2026-63086

text-generation-inference through 3.3.7 contains a server-side request forgery SSRF vulnerability in the OpenAI-compatible multimodal chat completions endpoint that allows unauthenticated network attackers to coerce the server into issuing arbitrary HTTP GET requests by supplying a crafted imageu...

CVE-2026-63086

The CVE-2026-63086 entry concerns text-generation-inference 3.3.7, with an SSRF flaw in the OpenAI-compatible multimodal chat completions endpoint. The fetch_image function in router/src/validation.rs does not validate addresses (private, loopback, link-local, or cloud metadata). The HTTP client ...

GHSA-29PF-2H5F-8G72 vulnerabilities

Vulnerabilities for packages: nemo, text-generation-inference, tritonserver-backend-vllm-cuda-12.9...

CVE-2026-4372 vulnerabilities

Vulnerabilities for packages: nemo, text-generation-inference, tritonserver-backend-vllm-cuda-12.9...

[SECURITY] Fedora 44 Update: sentencepiece-0.2.1-1.fc44

The SentencePiece is an unsupervised text tokenizer for Neural Network-based text generation. It is an unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabulary size is predetermined prior to the neural model training. SentencePiece...

CVE-2026-35483

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadtemplate allows reading files with .jinja, .jinja2, .yaml, or .yml extensions from anywhere on the server filesystem. For .jinja files the...

CVE-2026-35485

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadgrammar allows reading any file on the server filesystem with no extension restriction. Gradio does not server-side validate dropdown value...

CVE-2026-35486

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, he superbooga and superboogav2 RAG extensions fetch user-supplied URLs via requests.get with zero validation — no scheme check, no IP filtering, no hostname allowlist. An attacker can access clo...

CVE-2026-35050

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.1.1, users can save extention settings in "py" format and in the app root directory. This allows to overwrite python files, for instance the "download-model.py" file could be overwritten. Then, thi...

CVE-2026-35486

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, he superbooga and superboogav2 RAG extensions fetch user-supplied URLs via requests.get with zero validation — no scheme check, no IP filtering, no hostname allowlist. An attacker can access clo...

CVE-2026-35487

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadprompt allows reading any .txt file on the server filesystem. The file content is returned verbatim in the API response. This vulnerability...

CVE-2026-35483

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadtemplate allows reading files with .jinja, .jinja2, .yaml, or .yml extensions from anywhere on the server filesystem. For .jinja files the...

CVE-2026-35485

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadgrammar allows reading any file on the server filesystem with no extension restriction. Gradio does not server-side validate dropdown value...

EUVD-2026-19672

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadprompt allows reading any .txt file on the server filesystem. The file content is returned verbatim in the API response. This vulnerability...

CVE-2026-35487

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadprompt allows reading any .txt file on the server filesystem. The file content is returned verbatim in the API response. This vulnerability...

CVE-2026-35487 text-generation-webui has a Path Traversal in load_prompt() — .txt file read without authentication

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, an unauthenticated path traversal vulnerability in loadprompt allows reading any .txt file on the server filesystem. The file content is returned verbatim in the API response. This vulnerability...

CVE-2026-35486 text-generation-webui has a SSRF in superbooga/superboogav2 extensions — no URL validation

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, he superbooga and superboogav2 RAG extensions fetch user-supplied URLs via requests.get with zero validation — no scheme check, no IP filtering, no hostname allowlist. An attacker can access clo...

CVE-2026-35486

CVE-2026-35486 affects text-generation-webui prior to 4.3, where the superbooga/superboogav2 RAG extensions fetch user-supplied URLs via requests.get() without validation. The root cause is lack of URL scheme validation, IP filtering, and hostname allowlisting, enabling an attacker to reach cloud...

EUVD-2026-19671

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, he superbooga and superboogav2 RAG extensions fetch user-supplied URLs via requests.get with zero validation — no scheme check, no IP filtering, no hostname allowlist. An attacker can access clo...

CVE-2026-35486 text-generation-webui has a SSRF in superbooga/superboogav2 extensions — no URL validation

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, he superbooga and superboogav2 RAG extensions fetch user-supplied URLs via requests.get with zero validation — no scheme check, no IP filtering, no hostname allowlist. An attacker can access clo...