CVE-2024-7764
8.1 · HIGHOverview
CVE-2024-7764 is a high-severity vulnerability. It was published on March 20, 2025 and has a CVSS 3.0 base score of 8.1 (HIGH).
This vulnerability has a CVSS 3.0 base score of 8.1, rated HIGH. It can be exploited remotely over the network. Some level of privileges is required for exploitation.
Technical Description
Vanna-ai v0.6.2 is vulnerable to SQL Injection due to insufficient protection against injecting additional SQL commands from user requests. The vulnerability occurs when the `generate_sql` function calls `extract_sql` with the LLM response. An attacker can include a semi-colon between a search data field and their own command, causing the `extract_sql` function to remove all LLM generated SQL and execute the attacker's command if it passes the `is_sql_valid` function. This allows the execution of user-defined SQL beyond the expected boundaries, notably the trained schema.
Remediation
Check the references section for vendor advisories, patches, and mitigation guidance. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
Frequently Asked Questions
What is CVE-2024-7764?
CVE-2024-7764 is a high-severity vulnerability. It was published on March 20, 2025 and has a CVSS 3.0 base score of 8.1 (HIGH).
How severe is CVE-2024-7764?
This vulnerability has a CVSS 3.0 base score of 8.1, rated HIGH. It can be exploited remotely over the network. Some level of privileges is required for exploitation.
How do I fix or remediate CVE-2024-7764?
Check the references section for vendor advisories, patches, and mitigation guidance. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
How can CyberStrike help with CVE-2024-7764?
CyberStrike's AI-powered security agents can automatically detect CVE-2024-7764 across your infrastructure using autonomous pentesting, DAST scanning, and HackBrowser. The platform continuously monitors for known vulnerabilities and provides actionable remediation guidance prioritized by real-world exploitability.
How CyberStrike Helps
AI agents map your attack surface to find vulnerabilities like this one.
Automated penetration testing that runs continuously, not just quarterly.
AI-driven PR review catches vulnerable dependencies before they ship.
Browser-based exploitation validates findings with real proof-of-concept.
Related HIGH CVEs from 2024
View all →Vladimir Kononovich, a Security Researcher has found a flaw that allows for a remote code execution
Team ENVY, a Security Research TEAM has found a flaw that allows for a remote code execution on the
SuiteCRM is an open-source Customer Relationship Management (CRM) software application. Prior to ver
ghtml is software that uses tagged templates for template engine functionality. It is possible to in
Joplin is a free, open source note taking and to-do application. A remote code execution (RCE) vulne
The TLS certificate validation code is flawed. An attacker can obtain a TLS certificate from the Sto
dnsjava is an implementation of DNS in Java. Records in DNS replies are not checked for their releva
eLabFTW is an open source electronic lab notebook for research labs. By uploading specially crafted
A cross-site scripting (XSS) vulnerability has been reported to affect several QNAP operating system
NVIDIA ConnectX Firmware contains a vulnerability where an attacker may cause an improper handling o
reNgine before 2.1.2 allows OS Command Injection if an adversary has a valid session ID. The attack
HCL DRYiCE MyXalytics is impacted by path traversal arbitrary file read vulnerability because it use