CVE-2026-43622: Mismatched Memory Management Routines in ggml-org llama.cpp
llama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new_1batch() allocates memory using malloc() while free_1batch() deallocates it using the C++ delete operator, causing heap metadata corruption. Attackers can trigger this memory management mismatch to cause denial of service through process crashes or potentially achieve arbitrary code execution depending on allocator state.
AI Analysis
Technical Summary
The vulnerability CVE-2026-43622 affects llama.cpp versions including build b1886 through b7445. It is caused by mismatched memory management routines in the LLaMA-Android JNI wrapper: memory allocated with malloc() in new_1batch() is freed using the C++ delete operator in free_1batch(). This double free and heap metadata corruption can be exploited to cause denial of service or potentially arbitrary code execution depending on the state of the memory allocator.
Potential Impact
Exploitation of this vulnerability can cause denial of service through application crashes. Depending on the allocator state, it may also allow an attacker to achieve arbitrary code execution. The CVSS 4.0 score of 8.5 reflects a high severity with local attack vector, low complexity, no privileges required, and user interaction needed.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. No official fix or temporary workaround has been provided at this time.
CVE-2026-43622: Mismatched Memory Management Routines in ggml-org llama.cpp
Description
llama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new_1batch() allocates memory using malloc() while free_1batch() deallocates it using the C++ delete operator, causing heap metadata corruption. Attackers can trigger this memory management mismatch to cause denial of service through process crashes or potentially achieve arbitrary code execution depending on allocator state.
CVSS v4.0
Score 8.5high
Affected software
ggml-org
llama.cpp
pkg:github/ggml-org/llama.cppRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability CVE-2026-43622 affects llama.cpp versions including build b1886 through b7445. It is caused by mismatched memory management routines in the LLaMA-Android JNI wrapper: memory allocated with malloc() in new_1batch() is freed using the C++ delete operator in free_1batch(). This double free and heap metadata corruption can be exploited to cause denial of service or potentially arbitrary code execution depending on the state of the memory allocator.
Potential Impact
Exploitation of this vulnerability can cause denial of service through application crashes. Depending on the allocator state, it may also allow an attacker to achieve arbitrary code execution. The CVSS 4.0 score of 8.5 reflects a high severity with local attack vector, low complexity, no privileges required, and user interaction needed.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. No official fix or temporary workaround has been provided at this time.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-05-01T18:22:45.640Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6a74ab40bf8831d539ec7475
Added to database: 08/06/2026, 15:41:52 UTC
Last enriched: 08/13/2026, 16:47:26 UTC
Last updated: 09/21/2026, 22:01:34 UTC
Views: 49
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.