The vulnerability of the encode_image function in the framework for working with Large Language Models (LLM) like LlamaIndex arises from an incorrect limitation on the path name to the restricted-access catalog. This vulnerability allows attackers to disclose protected information.

The vulnerability of the encodeimage function in the LlamaIndex framework, which is used for working with large language models, is related to an incorrect restriction on the path name of the restricted-access catalog. Exploiting this vulnerability could allow a malicious actor to disclose...