AI Sec Watch

Gradio, an open-source Python package for building web applications around machine learning models, has a security flaw in its Access Control List (ACL, a system that controls which files users can access). Attackers can bypass this protection on Windows and macOS by changing the capitalization of file paths, since these operating systems treat uppercase and lowercase letters as the same in file names. This allows unauthorized access to sensitive files that should be blocked.

A vulnerability in Rasa (an open source machine learning framework) allows an attacker to achieve RCE (remote code execution, where an attacker runs commands on a system they don't own) by loading a malicious model if the HTTP API is enabled and authentication is not properly configured. The vulnerability only affects instances where the API is explicitly enabled (not the default) and lacks proper security controls.

The AI Scribe WordPress plugin (versions up to 2.3) has a vulnerability where it fails to check user permissions before allowing changes to plugin settings. This means that attackers with basic Subscriber-level access can modify the plugin's configuration without proper authorization.

The AI Scribe WordPress plugin (version 2.3 and earlier) has a SQL injection vulnerability (a flaw where attackers can insert malicious database commands) in its article builder feature that allows authenticated users with Contributor-level access to extract sensitive information from the website's database. The vulnerability exists because the plugin doesn't properly clean up user input before using it in database queries.

The AI Scribe WordPress plugin (versions up to 2.3) has a CSRF vulnerability (cross-site request forgery, where an attacker tricks a logged-in admin into unknowingly making changes to the site). Because the plugin fails to properly validate nonces (security tokens that prevent forged requests), an attacker can trick a site administrator into clicking a malicious link that changes the plugin's settings without the admin's knowledge.

Keras version 3.7.0 has a vulnerability where attackers can write arbitrary files (files placed anywhere on your system) to a user's machine by tricking the get_file function (a tool that downloads files) into downloading a malicious tar file (a compressed file format). This happens because the function doesn't properly verify that downloaded files are legitimate before using them.

A WordPress plugin called 'The Post Saint' (used to generate AI text and images) has a security flaw in versions up to 1.3.1 where it fails to check user permissions and validate file types when uploading files. This allows attackers with basic user accounts to upload malicious files that could let them execute arbitrary code (RCE, running unauthorized commands) on the website.

A security researcher demonstrated at Black Hat Europe how prompt injection (tricking an AI by hiding instructions in its input) can be used to create a Command and Control system (C2, a central server that remotely directs compromised systems) that remotely controls multiple ChatGPT instances. An attacker could compromise ChatGPT instances and force them to follow updated instructions from this central C2 system, potentially impacting all aspects of the CIA security triad (confidentiality, integrity, and availability of data).

LangChain4j-AIDeepin, a RAG (retrieval-augmented generation, where an AI pulls in external documents to answer questions) project, uses MD5 (a weak cryptographic hashing function) to hash files in versions before 3.5.0, which can cause file upload conflicts when different files produce the same hash value. This vulnerability has a CVSS score (a 0-10 rating of how severe a vulnerability is) of 6.9 and is classified as medium severity.