Answer in brief
CVE-2026-43629 records a High severity (CVSS 8.1) vulnerability in llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore. The current sources do not mark it as known exploited. The current feed maps ggml-org/llama.cpp (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.1. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps ggml-org/llama.cpp (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| ggml-org/llama.cppgeneric | b4882 || 0.16.1 | Not reported |
Published upstream
Aug 6, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Aug 6, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 6, 2026
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.
Quoted source text, attributed separately from HOL analysis.
Answer in brief
CVE-2026-43629 records a High severity (CVSS 8.1) vulnerability in llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore. The current sources do not mark it as known exploited. The current feed maps ggml-org/llama.cpp (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 8.1. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps ggml-org/llama.cpp (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| ggml-org/llama.cppgeneric | b4882 || 0.16.1 | Not reported |
Published upstream
Aug 6, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Aug 6, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Aug 6, 2026
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.
Quoted source text, attributed separately from HOL analysis.