CVE-2024-5826
Remote Code Execution via Prompt Injection in vanna-ai/vanna
Vexday Risk Score
28Low
SSVC decision (CISA)
Track
No exploitation signal → monitor
CVSS 9.8EPSS 0.9%KEV nãoPoC —Nuclei —Metasploit —Patch —
Lifecycle
27 Jun 2024Published on NVD
Recommendation: Monitor — no exploitation signal at the moment.
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.
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Affected products
vanna-ai · vanna-ai/vannaWant to know if your infrastructure is exposed to this?
Talk to TrueHacking →