CVE-2025-53630
llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the gguf_init_from_file_impl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579.
Scoring
- Severity
- HIGH
- CVSS base score
- 8.9
- CVSS vector
- CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:P
- EPSS probability
- 0.32%
- CWE
- CWE-122, CWE-680
- Published
- 2025-07-10
- Last modified
- 2026-03-13
Affected products
- ggml-org llama.cpp
Weakness type
Related vulnerabilities
- CVE-2026-85103 — Heap-based Buffer Overflow in VPN Certificate ASN.1 Decoding
- CVE-2026-87430 — Buffer overflow in WebRTC in Google Chrome prior to 153.0.8010.36 allowed a remote attacker to...
- CVE-2026-87579 — Buffer overflow in WebRTC in Google Chrome prior to 153.0.8010.36 allowed a remote attacker to...
- CVE-2026-87654 — Buffer overflow in ANGLE in Google Chrome on on Windows prior to 153.0.8010.36 allowed a remote...
- CVE-2026-87527 — Buffer overflow in WebGL in Google Chrome prior to 153.0.8010.36 allowed a remote attacker to...
- CVE-2026-53938 — OpenIDC/cjose has a heap buffer overflow in AES Key Wrap decryption (A128KW/A192KW/A256KW)
- CVE-2026-81993 — Acrobat Reader | Heap-based Buffer Overflow (CWE-122)
- CVE-2026-81992 — Acrobat Reader | Heap-based Buffer Overflow (CWE-122)