CVE-2024-48140

A prompt injection vulnerability in the chatbox of Butterfly Effect Limited Monica Your AI Copilot powered by ChatGPT4 v6.3.0 allows attackers to access and exfiltrate all previous and subsequent chat data between the user and the AI assistant via a crafted message...

CVE-2024-48145

A prompt injection vulnerability in the chatbox of Netangular Technologies ChatNet AI Version v1.0 allows attackers to access and exfiltrate all previous and subsequent chat data between the user and the AI assistant via a crafted message...

CVE-2023-4668

The Ad Inserter for WordPress is vulnerable to Sensitive Information Exposure in versions up to, and including, 2.7.30 via the ai-debug-processing-fe URL parameter. This can allow unauthenticated attackers to extract sensitive data including installed plugins present and active, active theme,...

CVE-2023-51527

Exposure of Sensitive Information to an Unauthorized Actor vulnerability in Senol Sahin AI Power: Complete AI Pack – Powered by GPT-4.This issue affects AI Power: Complete AI Pack – Powered by GPT-4: from n/a through 1.8.2...

CVE-2023-51419

Unrestricted Upload of File with Dangerous Type vulnerability in Bertha.Ai BERTHA AI. Your AI co-pilot for WordPress and Chrome.This issue affects BERTHA AI. Your AI co-pilot for WordPress and Chrome: from n/a through 1.11.10.7...

CVE-2023-6985

The 10Web AI Assistant – AI content writing assistant plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the installplugin AJAX action in all versions up to, and including, 1.0.18. This makes it possible for authenticated attackers, with...

CVE-2023-24415

Cross-Site Request Forgery CSRF vulnerability in QuantumCloud AI ChatBot plugin = 4.2.8 versions...

CVE-2023-48741

Improper Neutralization of Special Elements used in an SQL Command 'SQL Injection' vulnerability in QuantumCloud AI ChatBot.This issue affects AI ChatBot: from n/a through 4.7.8...

GitLab Duo Vulnerability Enabled Attackers to Hijack AI Responses with Hidden Prompts

Cybersecurity researchers have discovered an indirect prompt injection flaw in GitLab's artificial intelligence AI assistant Duo that could have allowed attackers to steal source code and inject untrusted HTML into its responses, which could then be used to direct victims to malicious websites...

CVE-2023-39631

An issue in LanChain-ai Langchain v.0.0.245 allows a remote attacker to execute arbitrary code via the evaluate function in the numexpr library...

CVE-2023-39661

An issue in pandas-ai v.0.9.1 and before allows a remote attacker to execute arbitrary code via the isjailbreak function...

CVE-2023-38699

MindsDB's AI Virtual Database allows developers to connect any AI/ML model to any datasource. Prior to version 23.7.4.0, a call to requests with verify=False disables SSL certificate checks. This rule enforces always verifying SSL certificates for methods in the Requests library. In version...

CVE-2023-33666

ai-dev aioptimizedcombinations before v0.1.3 was discovered to contain a SQL injection vulnerability via the component /includes/ajax.php...

CVE-2023-33663

In the module “Customization fields fee for your store” aicustomfee from ai-dev module for PrestaShop, an attacker can perform SQL injection up to 0.2.0. Release 0.2.1 fixed this security issue...

CVE-2023-3175

The AI ChatBot WordPress plugin before 4.6.1 does not adequately escape some settings, allowing high-privilege users such as admin to perform Cross-Site Scripting attacks even when the unfilteredhtml capability is disallowed...

CVE-2023-30710

Improper input validation vulnerability in Knox AI prior to SMR Sep-2023 Release 1 allows local attackers to launch privileged activities...

CVE-2023-28380

Uncontrolled search path for the IntelR AI Hackathon software before version 2.0.0 may allow an unauthenticated user to potentially enable escalation of privilege via network access...

CVE-2023-2742

The AI ChatBot WordPress plugin before 4.5.5 does not sanitize and escape its settings, allowing high-privilege users such as admin to perform Cross-Site Scripting attacks even when the unfilteredhtml capability is disallowed...

CVE-2023-2606

The WP Brutal AI WordPress plugin before 2.06 does not sanitise and escape some of its settings, which could allow high privilege users such as admin to perform Stored Cross-Site Scripting attacks even when the unfilteredhtml capability is disallowed for example in multisite setup...

CVE-2023-2580

The AI Engine WordPress plugin before 1.6.83 does not sanitize and escape some of its settings, which could allow high-privilege users such as admin to perform Stored Cross-Site Scripting attacks even when the unfilteredhtml capability is disallowed for example, in multisite setup...