CVE-2024-4181: high-severity vulnerability in run-llama/llama_index
Command Injection in run-llama/llama_index
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
21Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 8.8epss 2.1%
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/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Affected products
run-llama · run-llama/llama_indexRelated CVEs — run-llama/llama_index
In the same product, most dangerous first.
CVE-2024-3271CRITICALCommand Injection in run-llama/llama_indexEPSS 2.9%CVE-2024-11958CRITICALSQL Injection in run-llama/llama_indexEPSS 1.4%CVE-2024-12909CRITICALSQL Injection to RCE in run-llama/llama_indexEPSS 1.4%CVE-2025-1753HIGHCommand Injection in LLama-Index CLI in run-llama/llama_indexEPSS 1.1%CVE-2024-3098CRITICALPrompt Injection leading to Arbitrary Code Execution in run-llama/llama_indexEPSS 1.0%CVE-2025-1750CRITICALSQL Injection in run-llama/llama_indexEPSS 0.9%