Skip to content
Threat Feed
Subscribe

Tag

LLM

5 briefs RSS
critical advisory

PraisonAI `multiedit` Tool Vulnerability Allows Arbitrary File Read/Write and RCE

A critical vulnerability in PraisonAI's `multiedit` tool, affecting versions prior to 4.6.61, enables threat actors to achieve arbitrary file read and write capabilities by influencing LLM agent tool arguments, leading to sensitive data exfiltration and potential remote code execution.

praisonai LLM AI supply-chain arbitrary-file-read arbitrary-file-write path-traversal RCE
3r 5t
critical advisory

OpenClaude Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input

A sandbox bypass vulnerability exists due to the `dangerouslyDisableSandbox` parameter being exposed as part of the BashTool input schema, allowing an untrusted LLM to bypass the sandbox for any command and achieve host-level code execution due to the default `allowUnsandboxedCommands: true` setting.

sandbox-bypass llm code-execution
3r 1t
high advisory

Open WebUI /responses Endpoint Authentication Bypass Vulnerability

The /responses endpoint in Open WebUI's OpenAI router lacks access control, allowing authenticated users to bypass per-model access controls and interact with any configured model, potentially leading to denial of service, model theft, and access policy bypass.

open-webui authentication-bypass llm owasp
2r
medium advisory

Suspicious Processes Connecting to Large Language Model Endpoints

This rule detects DNS queries to known Large Language Model (LLM) domains by unsigned binaries or common Windows scripting utilities, indicating potential command and control activity leveraging LLMs for dynamic actions on compromised systems.

command_and_control malware llm
3r 1t
critical advisory

LiteLLM Package Compromised with Credential-Stealing Code via Trivy

The LiteLLM package was compromised and infected with credential-stealing code through a supply chain attack leveraging the Trivy vulnerability scanner.

supply-chain credential-theft llm trivy
2r 1t