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

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.

Published: 2024-06-27 Last update: 2026-06-17 Assigner: [email protected] Source: [email protected]

Conclusion & alert: CVE-2024-5826 is rated Moderate Risk (53.1/100): CVSS Critical severity, with medium exploitation likelihood (EPSS 0.88%). Mandatory action: Review affected assets and schedule remediation.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2024-5826

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-06-15 7.48% 0.88% -6.61%
2 2026-01-23 4.08% 7.48% +3.40%
3 2025-11-21 4.08%

Full EPSS history (16 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2024-5826

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
9.8 3.0 CRITICAL
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
3.9 5.9 [email protected]

Weakness enumeration for CVE-2024-5826

GitHub Security Advisory for CVE-2024-5826

GHSA-rrqq-fv6m-692m · Severity: critical · Ecosystem: pip — vanna vulnerable to remote code execution caused by prompt injection

Affected software / configurations for CVE-2024-5826

Vendor Product Version Raw CPE
No affected products in dataset.

References for CVE-2024-5826

cvelogic Threat Intelligence