CVE-2024-7764
Vanna-ai v0.6.2 is vulnerable to SQL Injection due to insufficient protection against injecting additional SQL commands from user requests.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.77%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.0
- 8.1 HIGHCVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
- EPSS
- 0.77% probability · 54th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-89
- Source
- security@huntr.dev
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.