HIGH8.8
PYSEC-2026-1565
RunGptLLM class in LlamaIndex has a command injection
Quick fix
PYSEC-2026-1565 — llama-index-llms-rungpt: upgrade to the fixed version with the command below.
pip install --upgrade 'llama-index-llms-rungpt>=0.1.3'Details
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.
Are you affected?
Enter the version of the package you're using.
Affected packages
PyPI/llama-index-llms-rungpt
Introduced in:
0Fixed in: 0.1.3Fix
pip install --upgrade 'llama-index-llms-rungpt>=0.1.3'References
- https://nvd.nist.gov/vuln/detail/CVE-2024-4181[ADVISORY]
- https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba[WEB]
- https://github.com/run-llama/llama_index[PACKAGE]
- https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1[WEB]
- https://pypi.org/project/llama-index-llms-rungpt[PACKAGE]
- https://github.com/advisories/GHSA-pw38-xv9x-h8ch[ADVISORY]