AI Sec Watch

CVE-2024-45852 is a vulnerability in MindsDB (a platform for building AI applications) versions 23.3.2.0 and newer that allows deserialization of untrusted data (converting untrusted incoming data back into executable code). An attacker can upload a malicious model that runs arbitrary code (any commands they choose) on the server when someone interacts with it.

A security flaw was found in the Chatbot with ChatGPT WordPress plugin (versions before 2.4.5) where certain REST routes (endpoints that external programs use to interact with the plugin) did not properly check user permissions, allowing anyone without logging in to delete error and chat logs.

A WordPress plugin called Chatbot Support AI (versions up to 1.0.2) has a security flaw where it fails to properly clean and filter certain settings, allowing admin users to inject malicious code through stored cross-site scripting (XSS, a type of attack where harmful scripts are saved and executed when users view a page). This vulnerability is particularly dangerous because it works even in multisite setups where HTML code is normally restricted.

Ollama before version 0.1.47 has a vulnerability in its extractFromZipFile function where it can extract files from a ZIP archive outside of the intended parent directory, a weakness called path traversal (CWE-22, where an attacker manipulates file paths to access directories they shouldn't). This could allow an attacker to write files to unintended locations on a system when processing a specially crafted ZIP file.

Microsoft 365 Copilot has a vulnerability that allows attackers to steal personal information like emails and MFA codes through a multi-step attack. The exploit uses prompt injection (tricking an AI by hiding malicious instructions in emails or documents), automatic tool invocation (making Copilot search for additional sensitive data without user permission), and ASCII smuggling (hiding data in invisible characters within clickable links) to extract and exfiltrate personal information.

CVE-2024-7110 is a vulnerability in GitLab EE (a code management platform) versions 17.0 through 17.3 that allows an attacker to execute arbitrary commands (run code of their choice) in a victim's pipeline through prompt injection (tricking the system by hiding malicious instructions in user input). This vulnerability affects multiple recent versions of the software.

The European AI Act assigns the European Commission's AI Office various responsibilities for regulating AI systems, including promoting AI literacy, overseeing biometric identification systems used by law enforcement, managing a registry of certified testing bodies (notified bodies that verify AI safety), and investigating whether these bodies remain competent. Most of these oversight duties take effect starting February or August 2025, with no specific deadlines given for completing individual tasks.

The EU AI Act requires member states to receive and register notifications about high-risk AI systems (AI systems that pose significant risks to safety or rights) from various parties, including law enforcement agencies using facial recognition systems, AI providers, importers, and organizations deploying these systems. These responsibilities take effect in two phases: August 2, 2025, and August 2, 2026, with member states also needing to assess conformity assessment bodies (independent organizations that verify AI systems meet safety standards) and share documentation with the European Commission.

A researcher discovered a security flaw in Google AI Studio where prompt injection (tricking an AI by hiding instructions in its input) allowed data exfiltration (stealing data) through HTML image tags rendered by the system. The vulnerability worked because Google AI Studio lacked a Content Security Policy (a security rule that restricts where a webpage can load resources from), making it possible to send data to unauthorized servers.