CRITICAL9.8

PYSEC-2026-396

llama-index-core Command Injection vulnerability

Quick fix

PYSEC-2026-396 — llama-index-core: upgrade to the fixed version with the command below.

pip install --upgrade 'llama-index-core>=0.10.24'

Details

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.

Are you affected?

Enter the version of the package you're using.

Affected packages

PyPI/llama-index-core

Introduced in: 0Fixed in: 0.10.24

Fixpip install --upgrade 'llama-index-core>=0.10.24'

References

https://nvd.nist.gov/vuln/detail/CVE-2024-3271[ADVISORY]
https://github.com/run-llama/llama_index/commit/2c92e88838a5f481d50840240b1dd3180066c6f5[WEB]
https://github.com/run-llama/llama_index/commit/5fbcb5a8b9f20f81b791c7fc8849e352613ab475[WEB]
https://github.com/run-llama/llama_index[PACKAGE]
https://huntr.com/bounties/9b32490e-7cf9-470e-8d49-ba083ae7a279[WEB]
https://pypi.org/project/llama-index-core[PACKAGE]
https://github.com/advisories/GHSA-r6gp-rff2-p3hf[ADVISORY]