We use these services and cookies to improve your user experience. You may opt out if you wish, however, this may limit some features on this site.
Please see our statement on Data Privacy.
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.
Reserved 2024-08-13 | Published 2025-03-20 | Updated 2025-03-20 | Assigner @huntr_aiCWE-89 Improper Neutralization of Special Elements used in an SQL Command
huntr.com/bounties/85d403b1-fbed-42e9-9ec1-2f79abf6eb0f
Support options