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.
{ "nvd_published_at": "2024-05-16T09:15:15Z", "cwe_ids": [ "CWE-94" ], "severity": "HIGH", "github_reviewed": true, "github_reviewed_at": "2024-05-16T17:47:36Z" }