PyPI package
vanna
pkg:pypi/vanna
Vulnerabilities (4)
| CVE | Sev | CVSS | KEV | Affected versions | Fixed in | Published | Description |
|---|---|---|---|---|---|---|---|
| CVE-2026-4229 | Hig | 7.3 | <= 2.0.2 | — | Mar 16, 2026 | A flaw has been found in vanna-ai vanna up to 2.0.2. This impacts the function remove_training_data of the file src/vanna/legacy/google/bigquery_vector.py. This manipulation of the argument ID causes sql injection. The attack can be initiated remotely. The exploit has been publis | |
| CVE-2024-5753 | Hig | 7.5 | <= 0.3.4 | — | Jul 5, 2024 | vanna-ai/vanna version v0.3.4 is vulnerable to SQL injection in some file-critical functions such as `pg_read_file()`. This vulnerability allows unauthenticated remote users to read arbitrary local files on the victim server, including sensitive files like `/etc/passwd`, by explo | |
| CVE-2024-5826 | Cri | 9.8 | <= 0.6.2 | — | Jun 27, 2024 | In the latest version of vanna-ai/vanna, the `vanna.ask` function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the `exec` function | |
| CVE-2024-5565 | Hig | 8.1 | <= 0.5.5 | — | May 31, 2024 | The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” |
- affected <= 2.0.2
A flaw has been found in vanna-ai vanna up to 2.0.2. This impacts the function remove_training_data of the file src/vanna/legacy/google/bigquery_vector.py. This manipulation of the argument ID causes sql injection. The attack can be initiated remotely. The exploit has been publis
- affected <= 0.3.4
vanna-ai/vanna version v0.3.4 is vulnerable to SQL injection in some file-critical functions such as `pg_read_file()`. This vulnerability allows unauthenticated remote users to read arbitrary local files on the victim server, including sensitive files like `/etc/passwd`, by explo
- affected <= 0.6.2
In the latest version of vanna-ai/vanna, the `vanna.ask` function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the `exec` function
- affected <= 0.5.5
The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask”