| शीर्षक | Mindinventory MindSQL v0.2.1 SQL Injection |
|---|
| विवरण | The vulnerability exists in the complete trust chain between user input, LLM output, and SQL execution. Malicious users can exploit this through prompt injection attacks, manipulating the LLM to generate arbitrary SQL statements that are then executed directly on the database server. The core issue stems from the system's implicit trust in LLM-generated SQL without any filtering or validation in the execution pipeline. |
|---|
| स्रोत | ⚠️ https://github.com/Ka7arotto/cve/blob/main/mindsql-text2sql/issue.md |
|---|
| उपयोगकर्ता | Goku (UID 80486) |
|---|
| सबमिशन | 06/03/2026 12:37 PM (3 महीनों पहले) |
|---|
| संयम | 20/03/2026 03:08 PM (14 days later) |
|---|
| स्थिति | स्वीकृत |
|---|
| VulDB प्रविष्टि | 352073 [Mindinventory MindSQL तक 0.2.1 mindsql_core.py ask_db SQL इंजेक्शन] |
|---|
| अंक | 19 |
|---|