CVE-2024-14021 (GCVE-0-2024-14021)
Vulnerability from cvelistv5 – Published: 2026-01-12 23:04 – Updated: 2026-07-28 01:47
VLAI
EPSS
VEX
Title
LlamaIndex <= 0.11.6 BGEM3Index Unsafe Deserialization
Summary
LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.load_from_disk() in llama_index/indices/managed/bge_m3/base.py. The function uses pickle.load() to deserialize multi_embed_store.pkl from a user-supplied persist_dir without validation. An attacker who can provide a crafted persist directory containing a malicious pickle file can trigger arbitrary code execution when the victim loads the index from disk.
Severity
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-01-13 16:23 UTC
CWE
- CWE-502 - Deserialization of Untrusted Data
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://huntr.com/bounties/ab4ceeb4-aa85-4d1c-aac… | technical-descriptionexploit |
| https://www.llamaindex.ai/ | product |
| https://github.com/run-llama/llama_index | third-party-advisory |
| https://www.vulncheck.com/advisories/llamaindex-b… | third-party-advisory |
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| run-llama | llama_index |
Affected:
0 , ≤ 0.11.6
(semver)
cpe:2.3:a:llamaindex:llamaindex:*:*:*:*:*:*:*:* |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-14021",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-01-13T16:23:29.155695Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-01-13T16:23:36.237Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unknown",
"packageURL": "pkg:github/run-llama/llama_index",
"product": "llama_index",
"repo": "https://github.com/run-llama/llama_index",
"vendor": "run-llama",
"versions": [
{
"lessThanOrEqual": "0.11.6",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"cpeApplicability": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:llamaindex:llamaindex:*:*:*:*:*:*:*:*",
"versionEndIncluding": "0.11.6",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "LifeTeam2024"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.load_from_disk() in llama_index/indices/managed/bge_m3/base.py. The function uses pickle.load() to deserialize multi_embed_store.pkl from a user-supplied persist_dir without validation. An attacker who can provide a crafted persist directory containing a malicious pickle file can trigger arbitrary code execution when the victim loads the index from disk."
}
],
"value": "LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.load_from_disk() in llama_index/indices/managed/bge_m3/base.py. The function uses pickle.load() to deserialize multi_embed_store.pkl from a user-supplied persist_dir without validation. An attacker who can provide a crafted persist directory containing a malicious pickle file can trigger arbitrary code execution when the victim loads the index from disk."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "LOCAL",
"baseScore": 8.4,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "ACTIVE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502 Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-28T01:47:42.445Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"tags": [
"technical-description",
"exploit"
],
"url": "https://huntr.com/bounties/ab4ceeb4-aa85-4d1c-aaca-4eda1b71fc12"
},
{
"tags": [
"product"
],
"url": "https://www.llamaindex.ai/"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://github.com/run-llama/llama_index"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/llamaindex-bgem3index-unsafe-deserialization"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "LlamaIndex \u003c= 0.11.6 BGEM3Index Unsafe Deserialization",
"x_generator": {
"engine": "Vulnogram 0.5.0"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2024-14021",
"datePublished": "2026-01-12T23:04:43.095Z",
"dateReserved": "2026-01-09T20:42:56.495Z",
"dateUpdated": "2026-07-28T01:47:42.445Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2024-14021",
"date": "2026-09-19",
"epss": "0.00329",
"percentile": "0.26299"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"defaultStatus": "unknown",
"packageURL": "pkg:github/run-llama/llama_index",
"product": "llama_index",
"repo": "https://github.com/run-llama/llama_index",
"vendor": "run-llama",
"versions": [
{
"lessThanOrEqual": "0.11.6",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"source": "disclosure@vulncheck.com"
}
],
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:llamaindex:llamaindex:*:*:*:*:*:*:*:*",
"matchCriteriaId": "C03B86D9-3F03-496D-A803-B1DC212F8FBF",
"versionEndIncluding": "0.11.6",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.load_from_disk() in llama_index/indices/managed/bge_m3/base.py. The function uses pickle.load() to deserialize multi_embed_store.pkl from a user-supplied persist_dir without validation. An attacker who can provide a crafted persist directory containing a malicious pickle file can trigger arbitrary code execution when the victim loads the index from disk."
},
{
"lang": "es",
"value": "Las versiones de LlamaIndex (run-llama/llama_index) hasta la 0.11.6 inclusive contienen una vulnerabilidad de deserializaci\u00f3n insegura en BGEM3Index.load_from_disk() en llama_index/indices/managed/bge_m3/base.py. La funci\u00f3n utiliza pickle.load() para deserializar multi_embed_store.pkl de un persist_dir proporcionado por el usuario sin validaci\u00f3n. Un atacante que pueda proporcionar un directorio persist_dir manipulado que contenga un archivo pickle malicioso puede desencadenar la ejecuci\u00f3n de c\u00f3digo arbitrario cuando la v\u00edctima carga el \u00edndice desde el disco."
}
],
"id": "CVE-2024-14021",
"lastModified": "2026-07-14T23:17:13.753",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 7.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 1.8,
"impactScore": 5.9,
"source": "nvd@nist.gov",
"type": "Primary"
}
],
"cvssMetricV40": [
{
"cvssData": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "LOCAL",
"availabilityRequirement": "NOT_DEFINED",
"baseScore": 8.4,
"baseSeverity": "HIGH",
"confidentialityRequirement": "NOT_DEFINED",
"exploitMaturity": "NOT_DEFINED",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "ACTIVE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2024-14021",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-01-13T16:23:29.155695Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-01-12T23:15:51.413",
"references": [
{
"source": "disclosure@vulncheck.com",
"tags": [
"Product"
],
"url": "https://github.com/run-llama/llama_index"
},
{
"source": "disclosure@vulncheck.com",
"tags": [
"Exploit",
"Third Party Advisory"
],
"url": "https://huntr.com/bounties/ab4ceeb4-aa85-4d1c-aaca-4eda1b71fc12"
},
{
"source": "disclosure@vulncheck.com",
"tags": [
"Product"
],
"url": "https://www.llamaindex.ai/"
},
{
"source": "disclosure@vulncheck.com",
"tags": [
"Third Party Advisory"
],
"url": "https://www.vulncheck.com/advisories/llamaindex-bgem3index-unsafe-deserialization"
}
],
"sourceIdentifier": "disclosure@vulncheck.com",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-502"
}
],
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
]
}
},
"redhat_vex": {
"current_release_date": "2026-01-13T23:20:28+00:00",
"cve": "CVE-2024-14021",
"id": "CVE-2024-14021",
"initial_release_date": "2024-01-01T00:00:00+00:00",
"product_status:known_not_affected": "1",
"source": "Red Hat CSAF VEX",
"status": "final",
"title": "LlamaIndex \u003c= 0.11.6 BGEM3Index Unsafe Deserialization",
"url": "https://security.access.redhat.com/data/csaf/v2/vex/2024/cve-2024-14021.json",
"version": "3"
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2024-14021",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-01-13T16:23:29.155695Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-01-13T16:23:32.528Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unknown",
"packageURL": "pkg:github/run-llama/llama_index",
"product": "llama_index",
"repo": "https://github.com/run-llama/llama_index",
"vendor": "run-llama",
"versions": [
{
"lessThanOrEqual": "0.11.6",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"cpeApplicability": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:llamaindex:llamaindex:*:*:*:*:*:*:*:*",
"versionEndIncluding": "0.11.6",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "LifeTeam2024"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.load_from_disk() in llama_index/indices/managed/bge_m3/base.py. The function uses pickle.load() to deserialize multi_embed_store.pkl from a user-supplied persist_dir without validation. An attacker who can provide a crafted persist directory containing a malicious pickle file can trigger arbitrary code execution when the victim loads the index from disk."
}
],
"value": "LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6 contain an unsafe deserialization vulnerability in BGEM3Index.load_from_disk() in llama_index/indices/managed/bge_m3/base.py. The function uses pickle.load() to deserialize multi_embed_store.pkl from a user-supplied persist_dir without validation. An attacker who can provide a crafted persist directory containing a malicious pickle file can trigger arbitrary code execution when the victim loads the index from disk."
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "LOCAL",
"baseScore": 8.4,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "ACTIVE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "CWE-502 Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-28T01:47:42.445Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"tags": [
"technical-description",
"exploit"
],
"url": "https://huntr.com/bounties/ab4ceeb4-aa85-4d1c-aaca-4eda1b71fc12"
},
{
"tags": [
"product"
],
"url": "https://www.llamaindex.ai/"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://github.com/run-llama/llama_index"
},
{
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/llamaindex-bgem3index-unsafe-deserialization"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "LlamaIndex \u003c= 0.11.6 BGEM3Index Unsafe Deserialization",
"x_generator": {
"engine": "Vulnogram 0.5.0"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2024-14021",
"datePublished": "2026-01-12T23:04:43.095Z",
"dateReserved": "2026-01-09T20:42:56.495Z",
"dateUpdated": "2026-07-28T01:47:42.445Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
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…