{"id":"CVE-2024-5826","aliases":["EUVD-2024-2162","GHSA-rrqq-fv6m-692m","PYSEC-2026-562"],"status":"published","title":"Remote Code Execution via Prompt Injection in vanna-ai/vanna","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.","severity":{"version":"3.0","score":9.8,"vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-10","score":0.00882,"percentile":0.59478,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-94"],"published":"2024-06-27T18:40:37Z","modified":"2026-07-01T20:23:10Z","affected":[{"source":"ghsa","ecosystem":"PyPI","package":"vanna","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"0.6.2"}]}]},{"source":"osv","ecosystem":"PyPI","package":"vanna","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"0.6.2"}]}],"versions":["0.0.1","0.0.10","0.0.11","0.0.12","0.0.13","0.0.14","0.0.15","0.0.16","0.0.17","0.0.18","0.0.19","0.0.2","0.0.20","0.0.21","0.0.22","0.0.23","0.0.24","0.0.25","0.0.26","0.0.27","0.0.28","0.0.29","0.0.3","0.0.30","0.0.31","0.0.32","0.0.33","0.0.34","0.0.35","0.0.36","0.0.37","0.0.38","0.0.4","0.0.5","0.0.6","0.0.7","0.0.8","0.0.9","0.1.0","0.1.1","0.2.0","0.2.1","0.3.0","0.3.1","0.3.2","0.3.3","0.3.4","0.4.0","0.4.1","0.4.2","0.4.3","0.5.0","0.5.1","0.5.2","0.5.3","0.5.4","0.5.5","0.6.0","0.6.1","0.6.2"]},{"source":"osv","ecosystem":"PyPI","package":"vanna","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"0.6.2"}]}],"versions":["0.0.1","0.0.10","0.0.11","0.0.12","0.0.13","0.0.14","0.0.15","0.0.16","0.0.17","0.0.18","0.0.19","0.0.2","0.0.20","0.0.21","0.0.22","0.0.23","0.0.24","0.0.25","0.0.26","0.0.27","0.0.28","0.0.29","0.0.3","0.0.30","0.0.31","0.0.32","0.0.33","0.0.34","0.0.35","0.0.36","0.0.37","0.0.38","0.0.4","0.0.5","0.0.6","0.0.7","0.0.8","0.0.9","0.1.0","0.1.1","0.2.0","0.2.1","0.3.0","0.3.1","0.3.2","0.3.3","0.3.4","0.4.0","0.4.1","0.4.2","0.4.3","0.5.0","0.5.1","0.5.2","0.5.3","0.5.4","0.5.5","0.6.0","0.6.1","0.6.2"]}],"products":[{"vendor":"vanna-ai","product":"vanna"},{"vendor":"vanna-ai","product":"vanna-ai/vanna"}],"references":[{"url":"https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369","tags":["x_transferred","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2024-5826","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-rrqq-fv6m-692m","tags":["advisory"]},{"url":"https://github.com/vanna-ai/vanna","tags":["package"]},{"url":"https://pypi.org/project/vanna","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2024-5826","title":"Remote Code Execution via Prompt Injection in vanna-ai/vanna","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.","status":"published","published":"2024-06-27T18:40:37.441Z","modified":"2025-10-15T12:50:29.876Z","cvss":[{"version":"3.0","score":9.8,"vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical","assessor":"cna"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T14:34:00.929382Z"}],"euvd":[{"id":"EUVD-2024-2162","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.","status":"published","published":"2024-06-27T18:40:37Z","modified":"2025-10-15T12:50:29Z","cvss":[{"version":"3.0","score":9.8,"vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical"}],"updated_at":"2026-11-02T20:31:32.071816Z"}],"ghsa":[{"id":"GHSA-rrqq-fv6m-692m","title":"vanna vulnerable to remote code execution caused by prompt injection","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.","status":"published","published":"2024-06-27T21:32:08Z","modified":"2024-06-28T21:08:25Z","cvss":[{"version":"3.0","score":9.8,"vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T14:37:55.455438Z"}],"nvd":[{"id":"CVE-2024-5826","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.","status":"published","published":"2024-06-27T19:15:17.35Z","modified":"2026-06-17T08:16:43.47Z","cvss":[{"version":"3.0","score":9.8,"vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical","assessor":"secondary"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T14:10:09.388795Z"}],"osv":[{"id":"GHSA-rrqq-fv6m-692m","title":"vanna vulnerable to remote code execution caused by prompt injection","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.","status":"published","published":"2024-06-27T21:32:08Z","modified":"2026-06-29T12:26:37.506344567Z","cvss":[{"version":"3.0","score":9.8,"vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T15:46:56.281047Z"},{"id":"PYSEC-2026-562","title":"vanna vulnerable to remote code execution caused by prompt injection","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.","status":"published","published":"2026-06-29T11:50:42.05216Z","modified":"2026-07-01T20:23:10.996611Z","cvss":[{"version":"3.0","score":9.8,"vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical"}],"updated_at":"2026-11-02T15:52:57.671918Z"}]}}