LlamaIndexGHSA-pw38-xv9x-h8ch
RunGptLLM class in LlamaIndex has a command injection
High8.8CVE-2024-4181 · Published May 16, 2024 · updated Jul 13, 2026
Affected versions
| Package | Affected | Fixed in |
|---|---|---|
| llama-index PyPI | < 0.10.13 | 0.10.13 |
Details and references
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.
- CVSS 3.0
- CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- Severity from
- GitHub (reviewed advisory)
- Weakness
- CWE-94
- Also known as
- CVE-2024-4181, PYSEC-2024-324, PYSEC-2026-1565
More LlamaIndex advisories
All LlamaIndex| Date | Advisory | Severity | Fixed in |
|---|---|---|---|
| Apr 162024 | llama-index-core Command Injection vulnerability CVE-2024-3271Critical9.8fixed in 0.10.24 | Critical9.8 | 0.10.24 |
| Apr 102024 | llama-index-core Prompt Injection vulnerability leading to Arbitrary Code Execution CVE-2024-3098Critical9.8fixed in 0.10.24 | Critical9.8 | 0.10.24 |
| Aug 222024 | LlamaIndex includes an exec call for `import {cls_name}` CVE-2024-45201Critical9.8fixed in 0.10.38 | Critical9.8 | 0.10.38 |
| Jan 222024 | SQL injection in llama-index CVE-2024-23751Critical9.8no fix yet | Critical9.8 | No fix yet |
| Aug 152023 | llama-index vulnerable to arbitrary code execution CVE-2023-39662Critical9.8fixed in 0.9.14 | Critical9.8 | 0.9.14 |
| Mar 202025 | LlamaIndex Improper Handling of Exceptional Conditions vulnerability CVE-2024-12704High7.5fixed in 0.12.6 | High7.5 | 0.12.6 |