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.
2024-05-16T09:15:15.553
2025-10-21T11:36:16.007
Analyzed
CVSSv3.0: 8.8 (HIGH)
| Type | Vendor | Product | Version/Range | Vulnerable? |
|---|---|---|---|---|
| Application | llamaindex | llamaindex | < 0.10.13 | Yes |