aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDataset
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

Browse All

All tracked items across vulnerabilities, news, research, incidents, and regulatory updates.

to
Export CSV
3312 items

CVE-2024-45854: Deserialization of untrusted data can occur in versions 23.10.3.0 and newer of the MindsDB platform, enabling a maliciou

highvulnerability
security
Sep 12, 2024
CVE-2024-45854

CVE-2024-45854 is a vulnerability in MindsDB (a platform for building AI applications) versions 23.10.3.0 and newer where deserialization of untrusted data (converting data from an external format back into executable code without checking if it's safe) allows an attacker to upload a malicious model that runs arbitrary code (any commands the attacker wants) on the server when a describe query is executed on it.

NVD/CVE Database

CVE-2024-45853: Deserialization of untrusted data can occur in versions 23.10.2.0 and newer of the MindsDB platform, enabling a maliciou

highvulnerability
security
Sep 12, 2024
CVE-2024-45853

CVE-2024-45853 is a vulnerability in MindsDB (a platform for building AI applications) versions 23.10.2.0 and newer where deserialization of untrusted data (the process of converting received data back into usable objects without checking if it's safe) allows an attacker to upload a malicious model that runs arbitrary code on the server when making predictions. This is a serious flaw because it gives attackers full control to execute whatever commands they want on the affected system.

CVE-2024-45852: Deserialization of untrusted data can occur in versions 23.3.2.0 and newer of the MindsDB platform, enabling a malicious

highvulnerability
security
Sep 12, 2024
CVE-2024-45852

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.

CVE-2024-6846: The Chatbot with ChatGPT WordPress plugin before 2.4.5 does not validate access on some REST routes, allowing for an una

mediumvulnerability
security
Sep 5, 2024
CVE-2024-6846

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.

CVE-2024-6722: The Chatbot Support AI: Free ChatGPT Chatbot, Woocommerce Chatbot WordPress plugin through 1.0.2 does not sanitise and e

mediumvulnerability
security
Sep 4, 2024
CVE-2024-6722

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.

CVE-2024-45436: extractFromZipFile in model.go in Ollama before 0.1.47 can extract members of a ZIP archive outside of the parent direct

highvulnerability
security
Aug 29, 2024
CVE-2024-45436EPSS: 29.1%

Microsoft Copilot: From Prompt Injection to Exfiltration of Personal Information

highnews
security
Aug 26, 2024

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: An issue was discovered in GitLab EE affecting all versions starting 17.0 to 17.1.6, 17.2 prior to 17.2.4, and 17.3 prio

mediumvulnerability
security
Aug 22, 2024
CVE-2024-7110

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 AI Act: Responsibilities of the European Commission (AI Office)

inforegulatory
policy
Aug 22, 2024

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 AI Act: Responsibilities of the EU Member States

inforegulatory
policy
Aug 22, 2024

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.

Google AI Studio: LLM-Powered Data Exfiltration Hits Again! Quickly Fixed.

mediumnews
security
Aug 21, 2024

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.

CVE-2024-43396: Khoj is an application that creates personal AI agents. The Automation feature allows a user to insert arbitrary HTML in

mediumvulnerability
security
Aug 20, 2024
CVE-2024-43396

Khoj, an application that creates personal AI agents, has a vulnerability in its Automation feature where users can insert arbitrary HTML and JavaScript code through the q parameter of the /api/automation endpoint due to improper input sanitization (a security flaw called stored XSS, where malicious code gets saved and runs when the page loads). This allows attackers to inject harmful code that affects other users viewing the page.

CVE-2024-6847: The Chatbot with ChatGPT WordPress plugin before 2.4.5 does not properly sanitise and escape a parameter before using it

criticalvulnerability
security
Aug 20, 2024
CVE-2024-6847

The Chatbot with ChatGPT WordPress plugin before version 2.4.5 has a SQL injection vulnerability (a type of attack where malicious code is inserted into database queries), which can be exploited by anyone without needing to log in when they submit messages to the chatbot. The plugin fails to properly sanitize and escape a parameter, meaning it doesn't clean or protect user input before using it in a SQL statement.

CVE-2024-6843: The Chatbot with ChatGPT WordPress plugin before 2.4.5 does not sanitise and escape user inputs, which could allow unaut

mediumvulnerability
security
Aug 19, 2024
CVE-2024-6843

The Chatbot with ChatGPT WordPress plugin before version 2.4.5 has a vulnerability where it does not properly clean and escape user inputs, allowing attackers to perform Stored Cross-Site Scripting attacks (XSS, a type of attack where malicious code gets saved and runs when admins view it) without needing to be logged in.

CVE-2024-42316: In the Linux kernel, the following vulnerability has been resolved: mm/mglru: fix div-by-zero in vmpressure_calc_level(

mediumvulnerability
security
Aug 17, 2024
CVE-2024-42316

A division-by-zero bug occurs in the Linux kernel's memory management when evict_folios() (a function that removes memory pages) incorrectly reduces a counter called nr_scanned, causing it to underflow and become zero. This zero value is later used as a divisor in vmpressure_calc_level() (a function that measures memory pressure), crashing the system.

CVE-2024-42474: Streamlit is a data oriented application development framework for python. Snowflake Streamlit open source addressed a s

mediumvulnerability
security
Aug 12, 2024
CVE-2024-42474

Streamlit (a Python framework for building data applications) had a path traversal vulnerability (a flaw that lets attackers access files outside their intended directory) in its static file sharing feature on Windows. An attacker could exploit this to steal the password hash (an encrypted version of a password) of the Windows user running Streamlit.

CVE-2024-6706: Attackers can craft a malicious prompt that coerces the language model into executing arbitrary JavaScript in the contex

mediumvulnerability
security
Aug 7, 2024
CVE-2024-6706

CVE-2024-6706 is a vulnerability where attackers can write malicious prompts that trick a language model into running arbitrary JavaScript (code that executes in a web browser) on a webpage. This is a type of cross-site scripting (XSS) attack, where untrusted input is not properly cleaned before being displayed on a web page, allowing attackers to inject malicious code.

CVE-2024-38206: An authenticated attacker can bypass Server-Side Request Forgery (SSRF) protection in Microsoft Copilot Studio to leak s

highvulnerability
security
Aug 6, 2024
CVE-2024-38206

CVE-2024-38206 is a vulnerability in Microsoft Copilot Studio where an authenticated attacker (someone with valid login credentials) can bypass SSRF protection (security that prevents a server from being tricked into making unwanted network requests) to leak sensitive information over a network.

CVE-2024-6331: stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI

highvulnerability
security
Aug 3, 2024
CVE-2024-6331

A vulnerability in the stitionai/devika AI project allows attackers to read sensitive files on a computer through prompt injection (tricking an AI by hiding malicious instructions in its input). The problem occurs because Google Gemini's safety filters were disabled, which normally prevent harmful outputs, leaving the system open to commands like reading `/etc/passwd` (a file containing user account information).

CVE-2024-38791: Server-Side Request Forgery (SSRF) vulnerability in Jordy Meow AI Engine: ChatGPT Chatbot allows Server Side Request For

mediumvulnerability
security
Aug 1, 2024
CVE-2024-38791

CVE-2024-38791 is a server-side request forgery (SSRF, a flaw where an attacker tricks a server into making unwanted requests to other systems) vulnerability in the Jordy Meow AI Engine: ChatGPT Chatbot plugin that affects versions up to 2.4.7. The vulnerability allows attackers to exploit this weakness to perform unauthorized actions by manipulating the plugin's server requests.

Previous112 / 166Next
NVD/CVE Database
NVD/CVE Database

Fix: Update the Chatbot with ChatGPT WordPress plugin to version 2.4.5 or later.

NVD/CVE Database
NVD/CVE Database

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.

Fix: Update Ollama to version 0.1.47 or later. The fix is available in the comparison between v0.1.46 and v0.1.47 (https://github.com/ollama/ollama/compare/v0.1.46...v0.1.47) and was implemented in pull request #5314 (https://github.com/ollama/ollama/pull/5314).

NVD/CVE Database
Embrace The Red
NVD/CVE Database
EU AI Act Updates
EU AI Act Updates
Embrace The Red

Fix: This vulnerability is fixed in version 1.15.0.

NVD/CVE Database
NVD/CVE Database

Fix: Update the Chatbot with ChatGPT WordPress plugin to version 2.4.5 or later.

NVD/CVE Database

Fix: The fix is to stop deducting scan_control->nr_scanned in evict_folios(), as stated in the source: 'fix the problem by not deducting scan_control->nr_scanned in evict_folios()'. This prevents the counter from underflowing and eliminates the zero divisor.

NVD/CVE Database

Fix: The vulnerability was patched on Jul 25, 2024, as part of Streamlit open source version 1.37.0.

NVD/CVE Database
NVD/CVE Database

Fix: Patch available from Microsoft Corporation at https://msrc.microsoft.com/update-guide/vulnerability/CVE-2024-38206

NVD/CVE Database
NVD/CVE Database
NVD/CVE Database