Lucene search

K
cve[email protected]CVE-2024-5826
HistoryJun 27, 2024 - 7:15 p.m.

CVE-2024-5826

2024-06-2719:15:17
CWE-94
web.nvd.nist.gov
13
vanna-ai
remote code execution
prompt injection
llm-generated code
exec function
backend server control

9.8 High

CVSS3

Attack Vector

NETWORK

Attack Complexity

LOW

Privileges Required

NONE

User Interaction

NONE

Scope

UNCHANGED

Confidentiality Impact

HIGH

Integrity Impact

HIGH

Availability Impact

HIGH

CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

9.9 High

AI Score

Confidence

High

0.0004 Low

EPSS

Percentile

9.1%

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.

CNA Affected

[
  {
    "vendor": "vanna-ai",
    "product": "vanna-ai/vanna",
    "versions": [
      {
        "version": "unspecified",
        "status": "affected",
        "versionType": "custom",
        "lessThanOrEqual": "latest"
      }
    ]
  }
]

9.8 High

CVSS3

Attack Vector

NETWORK

Attack Complexity

LOW

Privileges Required

NONE

User Interaction

NONE

Scope

UNCHANGED

Confidentiality Impact

HIGH

Integrity Impact

HIGH

Availability Impact

HIGH

CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

9.9 High

AI Score

Confidence

High

0.0004 Low

EPSS

Percentile

9.1%

Related for CVE-2024-5826