High Memory corruption

CVE-2026-43629 — llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking, allowing attackers with write access to the slot_save_path directory to corrupt heap memory. Attackers can craft malicious state files where cell_count multiplication overflows or exceeds tensor buffer allocation to write attacker-controlled bytes past buffer boundaries, potentially resulting in heap metadata corruption, model weight corruption, or arbitrary code execution via function pointer overwrite.

Published Aug 6, 2026 · Updated Oct 15, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: VulnCheck

Low

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.

How the score was calculated

EPSS 0.7% (30-day exploitation probability)+8
Technical severity (high)+6

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation

Not confirmed

Not in CISA KEV — an absence of record, not proof it is unexploited.

EPSS FIRST

0.7%

ahead of 52% of scored CVEs · Oct 15, 2026

Affects

Ggml

Llama.cpp

CVSS base

8.1

High · 2 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation

None

none · proof-of-concept · active

Automatable

can an attacker script the kill-chain steps

Technical impact

Total

partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

Documented patch — github.com (NIST National Vulnerability Database)
Documented patch — www.vulncheck.com (NIST National Vulnerability Database)

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

Identify exposed assets running the affected vendor/product/version combinations (Ggml Llama.cpp, Ggml-org Llama.cpp).
The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
Apply the fixed version or the patch documented under Remediation.
Search available logs for exploit probes matching the vulnerability class (memory corruption), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

Vendor	Product	Versions	Status	Source
Ggml	Llama.cpp	≥ b4882 and ≤ b9058	Vulnerable	NIST National Vulnerability Database
Ggml-org	Llama.cpp	≥ b4882 and ≤ b9058≥ 0.16.1 and ≤ 0.17.1	Vulnerable	CVE Program (cve.org) e CISA ADP

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector

Network

Attack complexity

High

Privileges required

None

User interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

Score	Version	Severity	Expl.	Impact	Scored by
9.2	CVSS 4.0	Critical	—	—	disclosure@vulncheck.com via NIST National Vulnerability Database
9.2	CVSS 4.0	Critical	—	—	VulnCheck via CVE Program (cve.org) e CISA ADP
8.1	CVSS 3.1	High	2.2	5.9	disclosure@vulncheck.com via NIST National Vulnerability Database
8.1	CVSS 3.1	High	—	—	VulnCheck via CVE Program (cve.org) e CISA ADP

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H (score shown at the top: disclosure@vulncheck.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-190 · Integer Overflow or Wraparound

Other CVEs with this weakness →

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
Correlate service crashes/restarts with inbound traffic; repeated crashes may indicate attempts.

web/proxy/WAF logsnetwork IDS/IPSendpoint telemetry (EDR)crash dumps

Timeline

What happened to this CVE, newest first.

2026
Affected products added · ggml-org/llama.cpp
Oct 15, 2026 · CVE Program (cve.org) e CISA ADP
SSVC assessment updated
Oct 15, 2026 · CVE Program (cve.org) e CISA ADP
Record published
Oct 15, 2026
Fix documented
Oct 15, 2026 · NIST National Vulnerability Database
CVSS changed · 8.1
Oct 15, 2026 · NIST National Vulnerability Database
Source status changed · → Analyzed
Oct 15, 2026 · NIST National Vulnerability Database
Record created in this database
Oct 15, 2026 · NIST National Vulnerability Database
CVE published
Aug 6, 2026 · VulnCheck

Source activity

Repeated readings are counted rather than listed.

1× Official description updated · Oct 15, 2026 – Oct 15, 2026

References

2 on the record

github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
Patch, Third Party Advisory, mitigation, NIST National Vulnerability Database
www.vulncheck.com/advisories/llama-cpp-b4882-b9058-buffer-overflow-in-kv-cache-state-re
Mitigation, Patch, Third Party Advisory, third-party-advisory, NIST National Vulnerability Database

Elsewhere on this site

Ggml
every CVE for this vendor

Memory corruption
same class

CWE-190
other pages naming this weakness

Related CVEs (same products)

High CVE-2026-107183 llama.cpp before b11393 Use-After-Free via common_chat_peg_mapper chat_parser 9d
Medium CVE-2026-86317 ggml-org llama.cpp RPC Server ggml-rpc.cpp deserialize_tensor assertion Sep 7, 2026
High CVE-2026-52132 Uncontrolled Recursion in Ggml Llama.cpp Sep 1, 2026
High CVE-2026-52130 Uncontrolled Recursion in Ggml Llama.cpp Sep 1, 2026
High CVE-2026-52131 llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function. Sep 1, 2026
Medium CVE-2026-78148 ggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp graph_compute null pointer dereference Aug 23, 2026

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-43629 is "llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore", rated High. It affects Llama.cpp (Ggml); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 8.1 describes technical severity. EPSS 0.70% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.