AI Security Threat Feed

cline: WebSocket auth bypass enables terminal RCE

Open WebUI has an LDAP Empty Password Authentication Bypass

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used...

vm2 NodeVM `nesting: true` bypasses `require: false` allowing sandbox escape and arbitrary OS command execution

Compromise of PyTorch Lightning PyPi Package Versions

Langflow Knowledge Bases API is Vulnerable to Path Traversal

Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file...

Gemini CLI: Remote Code Execution via workspace trust and tool allowlisting bypasses

LiteLLM has SQL Injection in Proxy API key verification

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, this vulnerability allows remote attackers to bypass...

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, Flowise is vulnerable to a critical unauthenticated...

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, an improper mass assignment (JSON injection)...

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, the specific flaw exists within the run method of the...

Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability

Flowise: Airtable_Agent Code Injection Remote Code Execution Vulnerability

OpenClaw: Feishu webhook and card-action validation now fail closed

Incomplete fix for CVE-2026-34935: Command Injection in MervinPraison/PraisonAI

Flowise CSVAgent: RCE via Python code injection

Flowise: RCE via MCP stdio command injection

OpenAI Codex CLI: RCE via malicious MCP config files