CVE-2026-43629
llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore
No known exploitation. EPSS puts it in the 53rd percentile. A vendor fix is available.
What to do
The vendor has published a fix. Version details are below where the sources state them.
- Ggml-org Llama.cppAffected: ≥ b4882, ≤ b9058Upgrade to: after b9058Affected: ≥ 0.16.1, ≤ 0.17.1Upgrade to: after 0.17.1Stated by: CVE record
Versions as the sources state them. Full version matrix after sign-in
What it is
From the CVE record
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.
In plain language
No plain-language summary for this CVE yet.
Exploitation
Where each signal puts this CVE on the scale from published to confirmed exploited.
- CISA KEV
Not in the catalog. CISA has not confirmed exploitation.
- Public exploits
No public exploit or proof of concept found in the sources we track.
- EPSS
0.7% chance of exploitation activity in the next 30 days, which ranks it in the 53rd percentile of scored CVEs.
Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.
Lifecycle
9 events over 46 days, from the signal feeds we watch.
- Patch availableworkaround available, record updated
- Record updated
- Record updated
- Publishedweakness classified, att&ck mapped, record updated
Affected products
Technical detail
CVSS 3.1 vector
Open in the CVSS calculatorCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Scored 8.1 by NVD.
How it is reached
- Attack Vector NetworkExploitable remotely over the network without any special conditions
- Attack Complexity HighRequires specific conditions like a race condition or non-default configuration
- Privileges Required NoneNo authentication required — anyone can exploit this
- User Interaction NoneNo user interaction needed — fully automated exploitation
Scope
- Scope UnchangedImpact is limited to the vulnerable component itself
Impact if exploited
- Confidentiality HighTotal information disclosure — all data in the component is compromised
- Integrity HighTotal loss of integrity — attacker can modify any data in the component
- Availability HighTotal denial of service — the component is completely unavailable
Weaknesses
ATT&CK techniques
Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.
- Initial AccessT1190Exploit Public-Facing Applicationhigh confidence
- Privilege EscalationT1068Exploitation for Privilege Escalationhigh confidence
Sources
Watch the software you run.
My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.
We'll flag the next CVE, public exploit or patch for Llama.cpp, not every advisory.
A free account adds
- The full version matrix and every affected product
- Exploit links, proofs of concept and Metasploit modules
- Email alerts for the products you watch
- The same data over REST API, MCP and CLI