Cyber Resilience

CVE-2024-14021

Deserialization in Llamaindex ≤ 0.11.6

Public PoCDeserialization
Published
12 January 2026
Modified
14 July 2026
Patch / advisory
CVSS Score v4 8.4
Click a component to see what it means
Raw vectorCVSS: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
EPSS Score 0.0028 20th percentile
Risk Priority 55 floored blend · peak EPSS

Summary

CVE-2024-14021 is a high-severity Deserialization of Untrusted Data (CWE-502) vulnerability in Llamaindex Llamaindex. Its CVSS base score is 8.4 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 20th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as NLP and Transformers; in the Supply Chain and Deployment risk domain.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.

Deeper analysis AI-assisted summary

Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.

CVE-2024-14021 is an unsafe deserialization vulnerability (CWE-502) in LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6. The flaw exists in the BGEM3Index.load_from_disk() function within llama_index/indices/managed/bge_m3/base.py, which invokes pickle.load() to deserialize the multi_embed_store.pkl file from a user-supplied persist_dir without validation. This allows deserialization of untrusted data loaded directly from disk.

An attacker can exploit the vulnerability by supplying a crafted persist directory containing a malicious pickle file. A victim who subsequently calls load_from_disk() on this directory will trigger arbitrary code execution. Per the CVSS v3.1 base score of 7.8 (AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H), exploitation requires local access, low complexity, no privileges, and user interaction to load the index, but grants high confidentiality, integrity, and availability impact.

Advisories and references, including those from VulnCheck (https://www.vulncheck.com/advisories/llamaindex-bgem3index-unsafe-deserialization), Huntr (https://huntr.com/bounties/ab4ceeb4-aa85-4d1c-aaca-4eda1b71fc12), the LlamaIndex GitHub repository (https://github.com/run-llama/llama_index), and the project site (https://www.llamaindex.ai/), provide further details on the issue and associated mitigations or patches. Security practitioners should consult these sources for remediation guidance.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

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…

more

a malicious pickle file can trigger arbitrary code execution when the victim loads the index from disk.

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Supply Chain and Deployment
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: llamaindex

Related Threats

MITRE ATT&CK Enterprise Techniques

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1203 Exploitation for Client Execution Execution
Adversaries may exploit software vulnerabilities in client applications to execute code.
T1210 Exploitation of Remote Services Lateral Movement
Adversaries may exploit remote services to gain unauthorized access to internal systems once inside of a network.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2024-12911Same product: Llamaindex Llamaindex
CVE-2025-6211Same product: Llamaindex Llamaindex
CVE-2024-12704Same product: Llamaindex Llamaindex
CVE-2025-3044Same product: Llamaindex Llamaindex
CVE-2025-7707Same product: Llamaindex Llamaindex
CVE-2024-58339Same product: Llamaindex Llamaindex
CVE-2025-3046Same product: Llamaindex Llamaindex
CVE-2025-1750Same product: Llamaindex Llamaindex
CVE-2024-23751Same product: Llamaindex Llamaindex
CVE-2025-1793Same product: Llamaindex Llamaindex

Affected Assets

llamaindex
llamaindex
≤ 0.11.6

Mitigating Controls

Mitigating Controls (NIST 800-53 r5) AI

Developer testing and evaluation can uncover deserialization flaws before deployment.

Input validation directly stops deserialization of untrusted data by ensuring inputs are valid before processing.

Engineering principles such as safe deserialization and input sanitization structurally prevent the weakness from being introduced.

Integrity verification tools can detect malformed or tampered serialized data after the fact.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-02 none match
prevents

PR.PS-02 addresses only post-deployment updates/patching and cannot prevent introduction of unsafe deserialization code, yet it can remediate some instances when the flaw exists in outdated libraries or components.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

finds

Security testing includes validation of deserialization routines and the use of untrusted data, reducing the likelihood that unsafe object reconstruction will be deployed.

prevents

Requiring vetted libraries, regular updates and SAST before release reduces the likelihood that deserialization logic will accept and act on attacker-controlled serialized objects.

finds

Regular scanning of third-party libraries and timely patching reduce the likelihood that unsafe deserialization vulnerabilities remain active.

none

Mandatory malware scanning of data received over networks or storage media intercepts malicious serialized payloads before they are deserialized by the target application.

References