CVE-2024-3271: Command Injection in run-llama/llama_index

Severity: critical (CVSS 9.8 v3.0)
Exploited in the wild: not listed in CISA KEV
EPSS: 2.9% probability of exploitation in the next 30 days
Public exploit or detection template: yes
Published: 2024-04-16 · updated 2026-06-17
Weakness: CWE-77

Description

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.

Affected products

run-llama/llama_index: from 0.10.6 before 0.10.26 — fixed in 0.10.26

How to fix

Upgrade to a fixed version: run-llama/llama_index 0.10.26. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2024-3271 or the next vulnerability affects your stack