Command Injection in run-llama/llama_index
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.
- Products
- Not specified
- Affected versions
- Not specified
- Fixed versions
- Not specified
- CVEs
- CVE-2024-4181
- Confirmed fixed CVEs
- Not specified
- Updated in this feed
- 7 Nov 2026, 12:06 UTC · Revision 1
Source evidence
Command Injection in run-llama/llama_index
core-osv · Original sourcePublished 16 May 2024, 09:03 UTC
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.
osv:CVE-2024-4181
Complete source record
{
"id": "39e1b677240515eb100c26aca9cd3e26549c01da649ea3a96d65e7bd15ecf15a",
"url": "https://osv.dev/vulnerability/CVE-2024-4181",
"method": "structured",
"payload": {
"kind": "advisory",
"title": "Command Injection in run-llama/llama_index",
"summary": "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.",
"evidence": "osv:CVE-2024-4181",
"products": [],
"severity": "high",
"structured": {
"id": "CVE-2024-4181",
"aliases": [
"CVE-2024-4181",
"GHSA-pw38-xv9x-h8ch",
"PYSEC-2024-324",
"PYSEC-2026-1565"
],
"metrics": [
{
"type": "CVSS_V3",
"score": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H"
}
],
"affected": [
{
"ranges": [
{
"repo": "https://github.com/run-llama/llama_index",
"type": "GIT",
"events": [
{
"introduced": "f8893ad2656036a58ea2284ec6cc2b3bc5a83283"
},
{
"fixed": "6d642a0893aced9bed026c5c15e17c41575ca024"
},
{
"fixed": "d73715eaf0642705583e7897c78b9c8dd2d3a7ba"
}
],
"database_specific": {
"extracted_events": [
{
"cpe": "cpe:2.3:a:llamaindex:llamaindex:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0.9.47"
},
{
"fixed": "0.10.13"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "d73715eaf0642705583e7897c78b9c8dd2d3a7ba"
}
],
"source": "REFERENCES_COMMIT"
}
]
}
}
],
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2024-4181.json"
}
}
],
"modified": "2026-10-28T02:30:50.855884448Z",
"provider": "osv",
"references": [
"https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1",
"https://github.com/CVEProject/cvelistV5/tree/main/cves/2024/4xxx/CVE-2024-4181.json",
"https://nvd.nist.gov/vuln/detail/CVE-2024-4181",
"https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"
],
"provider_metadata": {
"cwe_ids": [
"CWE-94"
],
"cna_assigner": "@huntr_ai",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2024/4xxx/CVE-2024-4181.json"
}
},
"related_cves": [
{
"value": "CVE-2024-4181",
"evidence": "/id"
}
],
"security_relevant": true,
"severity_evidence": "/severity/0/score"
},
"source_id": "core-osv",
"document_id": 519232,
"published_at": "2024-05-16T09:03:47.278+00:00"
}