llama-index-core Prompt Injection vulnerability leading to Arbitrary Code Execution
Critical severity
GitHub Reviewed
Published
Apr 10, 2024
to the GitHub Advisory Database
•
Updated Apr 10, 2024
Description
Published by the National Vulnerability Database
Apr 10, 2024
Published to the GitHub Advisory Database
Apr 10, 2024
Reviewed
Apr 10, 2024
Last updated
Apr 10, 2024
A vulnerability was identified in the
exec_utils
class of thellama_index
package, specifically within thesafe_eval
function, allowing for prompt injection leading to arbitrary code execution. This issue arises due to insufficient validation of input, which can be exploited to bypass method restrictions and execute unauthorized code. The vulnerability is a bypass of the previously addressed CVE-2023-39662, demonstrated through a proof of concept that creates a file on the system by exploiting the flaw.References