{"uuid": "00db4199-4965-4b70-a29b-0fe3cfdb6abf", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "2a075640-a300-48a4-bb44-bc6130783b9b", "vulnerability": "CVE-2024-7764", "type": "published-proof-of-concept", "source": "https://t.me/DarkWebInformer_CVEAlerts/8188", "content": "\ud83d\udd17 DarkWebInformer.com - Cyber Threat Intelligence\n\ud83d\udccc CVE ID: CVE-2024-7764\n\ud83d\udd25 CVSS Score: 8.1 (cvssV3_0, Vector: CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N)\n\ud83d\udd39 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.\n\ud83d\udccf Published: 2025-03-20T10:11:35.662Z\n\ud83d\udccf Modified: 2025-03-20T10:11:35.662Z\n\ud83d\udd17 References:\n1. https://huntr.com/bounties/85d403b1-fbed-42e9-9ec1-2f79abf6eb0f", "creation_timestamp": "2025-03-20T10:19:27.000000Z"}