AI Security Threat Feed

Open-WebUI: unauthenticated DoS via code formatter

H2O-3: unauthenticated AST parser enables DoS + file write

MLflow: CSRF in signup allows rogue account creation

MLflow: GraphQL DoS disables ML tracking server

Ollama: DoS via malicious GGUF model file upload

Ollama: GGUF model upload causes memory exhaustion DoS

Ollama: null pointer DoS via malicious GGUF model upload

BentoML: DoS via multipart boundary exhausts server

Gradio: DoS via malformed multipart boundary

MLflow: path traversal allows arbitrary file read via DBFS

ollama: divide-by-zero DoS via crafted GGUF model import

Open-WebUI: SSRF via unchecked OpenAI URL leaks internal secrets

llama-index: SQLi+DoS via prompt injection in query engine

Transformers: ReDoS in Nougat tokenizer causes DoS

llama-index: DoS via infinite loop in LangChain LLM

Ollama: DoS via malicious gguf model file upload

GPT Academic: SSRF in Markdown plugin leaks credentials

GPT Academic: SSRF via unsanitized HotReload plugin

Gradio: path traversal enables arbitrary file deletion DoS

Gradio: ReDoS in DateTime causes CPU exhaustion DoS