llama-index-llms-rungpt
Affected
- introduced
0, fixed0.1.3(ecosystem)
Fixed versions
0.1.3
Fix
- Fixed version
0.1.3pip install --upgrade llama-index-llms-rungpt==0.1.3
Advisory
Also known as: CVE-2024-4181, GHSA-pw38-xv9x-h8ch, PYSEC-2024-324
RunGptLLM class in LlamaIndex has a command injection
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.
High Basis: CVSS v3 score 8.8, vector CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
0, fixed 0.1.3 (ecosystem)0.1.3
0.1.3pip install --upgrade llama-index-llms-rungpt==0.1.3Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0