Cyber Resilience

CVE-2024-12704

DoS in Llamaindex 0.12.5

Public PoCDoS
Published
20 March 2025
Modified
15 October 2025
Patch / advisory
CVSS Score v3 7.5
Click a component to see what it means
Raw vectorCVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
EPSS Score 0.0076 52th percentile
Risk Priority 59 floored blend · peak EPSS

Summary

CVE-2024-12704 is a high-severity Infinite Loop (CWE-835) vulnerability in Llamaindex Llamaindex. Its CVSS base score is 7.5 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Application or System Exploitation (T1499.004); ranked in the top 48% of CVEs by exploit likelihood; 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 Other ATLAS/OWASP Terms risk domain.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-2 (Flaw Remediation) — see the control section below for these in your framework.

EU & UK References

Vulnerability Data

A vulnerability in the LangChainLLM class of the run-llama/llama_index repository, version v0.12.5, allows for a Denial of Service (DoS) attack. The stream_complete method executes the llm using a thread and retrieves the result via the get_response_gen method of the StreamingGeneratorCallbackHandler…

more

class. If the thread terminates abnormally before the _llm.predict is executed, there is no exception handling for this case, leading to an infinite loop in the get_response_gen function. This can be triggered by providing an input of an incorrect type, causing the thread to terminate and the process to continue running indefinitely.

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Other ATLAS/OWASP Terms
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: llm

Related Threats

MITRE ATT&CK Enterprise Techniques

T1499.004 Application or System Exploitation Impact
Adversaries may exploit software vulnerabilities that can cause an application or system to crash and deny availability to users.
T1499 Endpoint Denial of Service Impact
Adversaries may perform Endpoint Denial of Service (DoS) attacks to degrade or block the availability of services to users.
T1499.003 Application Exhaustion Flood Impact
Adversaries may target resource intensive features of applications to cause a denial of service (DoS), denying availability to those applications.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2024-58339Same product: Llamaindex Llamaindex
CVE-2025-3225Same product: Llamaindex Llamaindex
CVE-2025-6211Same product: Llamaindex Llamaindex
CVE-2025-3044Same product: Llamaindex Llamaindex
CVE-2024-12911Same product: Llamaindex Llamaindex
CVE-2025-7707Same product: Llamaindex Llamaindex
CVE-2024-14021Same product: Llamaindex Llamaindex
CVE-2025-1752Same product: Llamaindex Llamaindex
CVE-2024-12910Same product: Llamaindex Llamaindex
CVE-2025-5472Same product: Llamaindex Llamaindex

Affected Assets

llamaindex
llamaindex
0.12.5

Mitigating Controls

Mitigating Controls (NIST 800-53 r5) AI

Developer testing and evaluation can discover unreachable loop exit conditions through static analysis, fuzzing, or execution tracing.

Flaw remediation processes identify and correct infinite-loop defects reported from testing or operations.

Requiring documented development processes and secure coding standards reduces introduction of loops whose termination conditions are unreachable.

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-06 mostly match
prevents

Secure SDLC practices (reviews, testing, static analysis) directly prevent introduction of infinite-loop defects.

ID.RA-01 partial match
prevents

Static analysis and vuln scanning during asset assessment can detect unreachable loop exits.

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 can uncover infinite-loop conditions before release.

prevents

Secure development life cycle mandates practices that can detect and prevent infinite-loop defects.

prevents

Application security requirements can specify loop-termination rules, indirectly reducing the weakness.

prevents

Secure coding standards directly address loop termination and prevent infinite loops.

none

Secure architecture principles encourage designs that avoid unreachable exit conditions.

none

Change management can require review of loop logic when code is modified.

References