Medium
6.9
llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader
CVE-2026-116829
First seen on SecPulse
Affected packages
| Ecosystem | Package | Affected | Fixed |
|---|---|---|---|
| ggml-org | llama.cpp |
≥ b10398, < b11301 ≥ 0.1.0, < 0.6.0 |
b11301 0.6.0 |
Fix status by distribution
Fixed packages published by each distribution for this CVE
- Debian DEBIAN-CVE-2026-116829 llama.cpp Fixed in: 1:0.6.0+dfsg-1
- Ubuntu UBUNTU-CVE-2026-116829 llama.cpp
Original description The description as published by the source.
llama.cpp b10398 before b11301 contains an integer overflow vulnerability in gguf_init_from_reader that allows attackers to bypass tensor element-count validation by supplying shapes whose product wraps to zero. Attackers can craft GGUF files with enormous tensor extents that overflow ggml_nbytes() and strides, causing out-of-bounds memory access when buffers are sized from wrapped byte counts.
Source: CVE.org (CVE Program・cvelistV5) NVD GitHub Advisory
References
- advisory github.com
- advisory vulncheck.com
- advisory nvd.nist.gov
- advisory github.com
- patch github.com
- patch github.com
- report github.com
- web github.com
- web github.com