CVE-2026-43630: Out-of-bounds Read in ggml-org llama.cpp
llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated cells array. Attackers can craft a malicious slot file with an oversized seq_id value to trigger an out-of-bounds read that leaks heap data including pointer values into server logs, defeating ASLR protections and facilitating further exploitation.
AI Analysis
Technical Summary
llama.cpp versions b5702 through b7653 contain an out-of-bounds read vulnerability (CWE-125) in the recurrent memory state restore path. Attackers who have write access to the slot save directory can create a malicious slot file with an oversized seq_id value that triggers reading beyond the allocated cells array. This results in leakage of heap memory data, including pointer values, into server logs. Such leakage can defeat Address Space Layout Randomization (ASLR) protections and facilitate further exploitation. The vulnerability is tracked as CVE-2026-43630 with a CVSS 4.0 score of 6.3 (medium severity). There is no vendor advisory or patch currently available, and no known exploits in the wild have been reported.
Potential Impact
The vulnerability allows an attacker with write access to the slot save directory to read memory beyond allocated bounds, leaking sensitive heap data including pointer values. This memory disclosure can undermine ASLR protections, increasing the risk of further exploitation. However, exploitation requires write access to the slot save directory, limiting the attack surface. No known active exploitation has been reported.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, restrict write access to the slot save directory to trusted users only to prevent attackers from crafting malicious slot files that trigger the vulnerability.
CVE-2026-43630: Out-of-bounds Read in ggml-org llama.cpp
Description
llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated cells array. Attackers can craft a malicious slot file with an oversized seq_id value to trigger an out-of-bounds read that leaks heap data including pointer values into server logs, defeating ASLR protections and facilitating further exploitation.
CVSS v4.0
Score 6.3medium
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
llama.cpp versions b5702 through b7653 contain an out-of-bounds read vulnerability (CWE-125) in the recurrent memory state restore path. Attackers who have write access to the slot save directory can create a malicious slot file with an oversized seq_id value that triggers reading beyond the allocated cells array. This results in leakage of heap memory data, including pointer values, into server logs. Such leakage can defeat Address Space Layout Randomization (ASLR) protections and facilitate further exploitation. The vulnerability is tracked as CVE-2026-43630 with a CVSS 4.0 score of 6.3 (medium severity). There is no vendor advisory or patch currently available, and no known exploits in the wild have been reported.
Potential Impact
The vulnerability allows an attacker with write access to the slot save directory to read memory beyond allocated bounds, leaking sensitive heap data including pointer values. This memory disclosure can undermine ASLR protections, increasing the risk of further exploitation. However, exploitation requires write access to the slot save directory, limiting the attack surface. No known active exploitation has been reported.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, restrict write access to the slot save directory to trusted users only to prevent attackers from crafting malicious slot files that trigger the vulnerability.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-05-01T18:22:45.641Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6a750702bf8831d5395f59c5
Added to database: 08/06/2026, 22:13:22 UTC
Last enriched: 08/14/2026, 15:54:37 UTC
Last updated: 09/21/2026, 22:01:34 UTC
Views: 38
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.