What’s Vulnerable › Vulnerabilities

CVE-2024-5826: Remote Code Execution via Prompt Injection in vanna-ai/vanna

• Severity: critical (CVSS 9.8 v3.0)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.9% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2024-06-27 · updated 2026-06-17
• Weakness: CWE-94

Description

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 in `src/vanna/base/base.py`. This vulnerability can be exploited by an attacker to achieve remote code execution on the app backend server, potentially gaining full control of the server.

Affected products

• vanna-ai vanna: 0

References

• https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369
• https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369

Get alerted when CVE-2024-5826 or the next vulnerability affects your stack