CVE-2024-4181 (GCVE-0-2024-4181)
Vulnerability from cvelistv5 – Published: 2024-05-16 09:03 – Updated: 2024-08-01 20:33
VLAI
EPSS
VEX
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.
Severity
8.8 (High)
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2024-05-16 16:10 UTC
CWE
- CWE-94 - Improper Control of Generation of Code
Assigner
References
Impacted products
2 products
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| run-llama | run-llama/llama_index |
Affected:
unspecified , < 0.10.13
(custom)
|
guessed | |
| run-llama | llama_index |
Affected:
0.9.47
cpe:2.3:a:run-llama:llama_index:*:*:*:*:*:*:*:* |
{
"containers": {
"adp": [
{
"affected": [
{
"cpes": [
"cpe:2.3:a:run-llama:llama_index:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "llama_index",
"vendor": "run-llama",
"versions": [
{
"status": "affected",
"version": "0.9.47"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-4181",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-05-16T16:10:22.479833Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-06-04T17:55:23.180Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
},
{
"providerMetadata": {
"dateUpdated": "2024-08-01T20:33:52.659Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"tags": [
"x_transferred"
],
"url": "https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"
},
{
"tags": [
"x_transferred"
],
"url": "https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"
}
],
"title": "CVE Program Container"
}
],
"cna": {
"affected": [
{
"product": "run-llama/llama_index",
"vendor": "run-llama",
"versions": [
{
"lessThan": "0.10.13",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "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\u0027s 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."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94 Improper Control of Generation of Code",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-05-16T09:03:47.278Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"
},
{
"url": "https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"
}
],
"source": {
"advisory": "1a204520-598a-434e-b13d-0d34f2a5ddc1",
"discovery": "EXTERNAL"
},
"title": "Command Injection in run-llama/llama_index"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-4181",
"datePublished": "2024-05-16T09:03:47.278Z",
"dateReserved": "2024-04-25T13:52:02.986Z",
"dateUpdated": "2024-08-01T20:33:52.659Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2024-4181",
"date": "2026-09-18",
"epss": "0.02135",
"percentile": "0.81173"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"product": "run-llama/llama_index",
"vendor": "run-llama",
"versions": [
{
"lessThan": "0.10.13",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"source": "security@huntr.dev"
},
{
"affectedData": [
{
"cpes": [
"cpe:2.3:a:run-llama:llama_index:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "llama_index",
"vendor": "run-llama",
"versions": [
{
"status": "affected",
"version": "0.9.47"
}
]
}
],
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
}
],
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:llamaindex:llamaindex:*:*:*:*:*:*:*:*",
"matchCriteriaId": "34FD9B1D-9DCA-4F40-A413-28B7CC8376E8",
"versionEndExcluding": "0.10.13",
"versionStartIncluding": "0.9.47",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "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\u0027s 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."
},
{
"lang": "es",
"value": "Existe una vulnerabilidad de inyecci\u00f3n de comandos en la clase RunGptLLM de la librer\u00eda llama_index, versi\u00f3n 0.9.47, utilizada por el marco RunGpt de JinaAI para conectarse a los modelos de aprendizaje de idiomas (LLM). La vulnerabilidad surge del uso inadecuado de la funci\u00f3n de evaluaci\u00f3n, lo que permite que un proveedor de alojamiento LLM malicioso o comprometido ejecute comandos arbitrarios en la m\u00e1quina del cliente. Este problema se solucion\u00f3 en la versi\u00f3n 0.10.13. La explotaci\u00f3n de esta vulnerabilidad podr\u00eda llevar a que un proveedor de alojamiento obtenga control total sobre las m\u00e1quinas cliente."
}
],
"id": "CVE-2024-4181",
"lastModified": "2026-06-17T08:01:16.973",
"metrics": {
"cvssMetricV30": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.0"
},
"exploitabilityScore": 2.8,
"impactScore": 5.9,
"source": "security@huntr.dev",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2024-4181",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-05-16T16:10:22.479833Z",
"version": "2.0.3"
}
}
]
},
"published": "2024-05-16T09:15:15.553",
"references": [
{
"source": "security@huntr.dev",
"tags": [
"Patch"
],
"url": "https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"
},
{
"source": "security@huntr.dev",
"tags": [
"Exploit",
"Third Party Advisory"
],
"url": "https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"
},
{
"source": "af854a3a-2127-422b-91ae-364da2661108",
"tags": [
"Patch"
],
"url": "https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"
},
{
"source": "af854a3a-2127-422b-91ae-364da2661108",
"tags": [
"Exploit",
"Third Party Advisory"
],
"url": "https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"
}
],
"sourceIdentifier": "security@huntr.dev",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-94"
}
],
"source": "security@huntr.dev",
"type": "Secondary"
}
]
}
},
"redhat_vex": {
"current_release_date": "2025-05-28T22:07:28+00:00",
"cve": "CVE-2024-4181",
"id": "CVE-2024-4181",
"initial_release_date": "2024-01-01T00:00:00+00:00",
"product_status:known_not_affected": "1",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "Command Injection in run-llama/llama_index",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2024/cve-2024-4181.json",
"version": "3"
},
"vulnrichment": {
"containers": {
"adp": [
{
"providerMetadata": {
"dateUpdated": "2024-08-01T20:33:52.659Z",
"orgId": "af854a3a-2127-422b-91ae-364da2661108",
"shortName": "CVE"
},
"references": [
{
"tags": [
"x_transferred"
],
"url": "https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"
},
{
"tags": [
"x_transferred"
],
"url": "https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"
}
],
"title": "CVE Program Container"
},
{
"affected": [
{
"cpes": [
"cpe:2.3:a:run-llama:llama_index:*:*:*:*:*:*:*:*"
],
"defaultStatus": "unknown",
"product": "llama_index",
"vendor": "run-llama",
"versions": [
{
"status": "affected",
"version": "0.9.47"
}
]
}
],
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-4181",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2024-05-16T16:10:22.479833Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2024-05-16T17:38:08.773Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "run-llama/llama_index",
"vendor": "run-llama",
"versions": [
{
"lessThan": "0.10.13",
"status": "affected",
"version": "unspecified",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "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\u0027s 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."
}
],
"metrics": [
{
"cvssV3_0": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.0"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94 Improper Control of Generation of Code",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2024-05-16T09:03:47.278Z",
"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"shortName": "@huntr_ai"
},
"references": [
{
"url": "https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"
},
{
"url": "https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"
}
],
"source": {
"advisory": "1a204520-598a-434e-b13d-0d34f2a5ddc1",
"discovery": "EXTERNAL"
},
"title": "Command Injection in run-llama/llama_index"
}
},
"cveMetadata": {
"assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
"assignerShortName": "@huntr_ai",
"cveId": "CVE-2024-4181",
"datePublished": "2024-05-16T09:03:47.278Z",
"dateReserved": "2024-04-25T13:52:02.986Z",
"dateUpdated": "2024-08-01T20:33:52.659Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.1"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.
Loading…