Vulnerabilities · 2024 · Llamaindex
CVE-2024-4181
Llamaindex vulnerability
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.
Affected products
Llamaindex. The exact versions are in the references.
What to do now
- Check your exposureFind out whether Llamaindex runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Limit access until thenIf you cannot update at once, take the system off the internet or restrict who can reach it.
References
- github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba · Patch
- huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1 · Exploit
- nvd.nist.gov/vuln/detail/CVE-2024-4181
- github.com/advisories/GHSA-pw38-xv9x-h8ch
- nvd.nist.gov/vuln/detail/CVE-2024-4181
- cve.org/CVERecord?id=CVE-2024-4181
More vulnerabilities in Llamaindex products
CVE-2025-7707CVE-2025-6211CVE-2025-6210CVE-2025-6209CVE-2025-5472CVE-2025-3225CVE-2025-3108CVE-2025-3046All 24
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.