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).
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (2.14%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
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.
- CVSS 3.0
- 8.8 HIGHCVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- EPSS
- 2.14% probability · 81th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-94
- Affected
- llamaindex/llamaindex
- Source
- security@huntr.dev
References
- https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7baPatch
- https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1Exploit, Third Party Advisory
- https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7baPatch
- https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1Exploit, Third Party Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.