CVE-2024-3098: llama_index code execution via prompt injection in safe_eval

Summary

A flaw in the `safe_eval` function of the `exec_utils` class in the `llama_index` package allows prompt injection to lead to arbitrary code execution. Insufficient input validation lets an attacker bypass method restrictions and run unauthorized code. It bypasses the previously addressed CVE-2023-39662, and a proof of concept creates a file on the system.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

• llama-index-corePyPILLM dependency since 2024-02-02 · 34 tracked dependents

Related items

• HighCVE-2024-58339: LlamaIndex VannaQueryEngine uncontrolled resource consumption in custom_querySame vendor · NVD/CVE Database
• HighGHSA-rg9h-vx28-xxp5: llama-index has Insecure Temporary FileSame vendor · GitHub Advisory Database
• HighGHSA-7753-xrfw-ch36: LlamaIndex affected by a Denial of Service (DOS) in JSONReaderSame vendor · GitHub Advisory Database
• MediumGHSA-5hq9-5r78-2gjh: LlamaIndex vulnerable to data loss through hash collisions in its DocugamiReader class Same vendor · GitHub Advisory Database
• HighGHSA-2rhq-96q8-4vjq: LlamaIndex vulnerable to Path Traversal attack through its encode_image functionSame vendor · GitHub Advisory Database