VulnerabilityDeferred

CVE-2024-5826

In the latest version of vanna-ai/vanna, the `vanna.ask` function is vulnerable to remote code execution due to prompt injection.

CRITICAL 9.8EPSS 0.88%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (0.88%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

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.

CVSS 3.0: 9.8 CRITICALCVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS: 0.88% probability · 57th percentile
CISA KEV: Not listed
Weakness: CWE-94
Source: security@huntr.dev

References

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.