Llamaindex: Security Vulnerabilities
An issue was discovered in llama_index before 0.10.38. download/integration.py includes an exec call for import {cls_name}.
CVSS Score
8.8
EPSS Score
0.002
Published
2024-08-22
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 Score
8.8
EPSS Score
0.016
Published
2024-05-16
A command injection vulnerability exists in the run-llama/llama_index repository, specifically within the safe_eval function. Attackers can bypass the intended security mechanism, which checks for the presence of underscores in code generated by LLM, to execute arbitrary code. This is achieved by crafting input that does not contain an underscore but still results in the execution of OS commands. The vulnerability allows for remote code execution (RCE) on the server hosting the application.
CVSS Score
9.8
EPSS Score
0.012
Published
2024-04-16
LlamaIndex (aka llama_index) through 0.9.34 allows SQL injection via the Text-to-SQL feature in NLSQLTableQueryEngine, SQLTableRetrieverQueryEngine, NLSQLRetriever, RetrieverQueryEngine, and PGVectorSQLQueryEngine. For example, an attacker might be able to delete this year's student records via "Drop the Students table" within English language input.
CVSS Score
9.8
EPSS Score
0.004
Published
2024-01-22
Page 3