CVE-2024-5826 json
Remote Code Execution via Prompt Injection in vanna-ai/vanna
published 2024-06-27 2 y ago modified 2026-07-01 4 mo ago also GHSA-rrqq-fv6m-692m , PYSEC-2026-562 , EUVD-2024-2162
- cvss
- 9.8
- version 3.0, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.9%
- EPSS 0.9% chance of exploitation in 30 days, percentile 59%
- public exploits
- 0
- none known
Summary
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.
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- total
- Assessed
- 2 y ago
Exploit prediction
0.88% chance of exploitation in the next 30 days, higher than 59% of all scored CVEs (FIRST EPSS, 2026-11-08).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.0 | 9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.0 | 9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.0 | 9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | vanna | <=0.6.2 |
no fix listed |
Affected products
- vanna-ai vanna-ai/vanna
- vanna-ai vanna
Classification
- Weakness
-
- CWE-94 Improper Control of Generation of Code
References
Sources
- CVE List CVE-2024-5826
- GitHub Advisory GHSA-rrqq-fv6m-692m
- NVD CVE-2024-5826
- OSV PYSEC-2026-562
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.