CVE-2026-43629
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Summary
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.
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| ggml-org | llama.cpp | b4882 <= b9058 | affected |
| ggml-org | llama.cpp | 0.16.1 <= 0.17.1 | affected |
Weaknesses
- CWE-787: CWE-787 Out-of-bounds Write
- CWE-190: CWE-190 Integer Overflow or Wraparound
References
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.