CVE-2024-3098 Prompt Injection leading to Arbitrary Code Execution in run-llama/llama_index

2024-04-1017:07:56

CWE-94

@huntr_ai

www.cve.org

vulnerability identified

exec_utils class

llama_index package

safe_eval function

prompt injection

arbitrary code execution

insufficient validation

method restrictions bypass

unauthorized code execution

previously addressed cve-2023-39662

proof of concept

system file creation

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

10 High

AI Score

Confidence

High

0.003 Low

EPSS

Percentile

68.1%

JSON

A vulnerability was identified in the exec_utils class of the llama_index package, specifically within the safe_eval function, allowing for prompt injection leading to arbitrary code execution. This issue arises due to insufficient validation of input, which can be exploited to bypass method restrictions and execute unauthorized code. The vulnerability is a bypass of the previously addressed CVE-2023-39662, demonstrated through a proof of concept that creates a file on the system by exploiting the flaw.

CNA Affected

[
  {
    "vendor": "run-llama",
    "product": "run-llama/llama_index",
    "versions": [
      {
        "version": "unspecified",
        "lessThan": "0.10.24",
        "status": "affected",
        "versionType": "custom"
      }
    ]
  }
]