RCE in Llamaindex
CVE-2024-4181
A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the RunGpt framework from JinaAI to connect to Language Learning Models (LLMs). The vulnerability arises from the improper use of the eval function, allowing a malicious or compromised LLM hosting provider to execute arbitrary commands on the client's machine. This issue was fixed in version 0.10.13. The exploitation of this vulnerability could lead to a hosting provider gaining full control over client machines.
Vulnerability class: RCE (Remote Code Execution)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 8.8 (High). Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.021, 82.3th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Llamaindex
- Run-Llama Run-Llama/llama Index — versions unspecified
Weakness classification (CWE)
Public exploits and proof-of-concept code
Also mentioned in 3 other repositories (XiaomingX/nice-juejin-article, XiaomingX/weekly, yux1azhengye/yux1azhengye). These reference the CVE in a list, notes or a scanner and are not exploit code for it.
References
- huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1 (Exploit, Third Party Advisory)
- github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba (Patch)