Skip to content
CVE
by OpenHack
Browse
All CVEs
Every CVE, newest first, with filters
CVEs by company
Microsoft, Cisco, Fortinet and 840 more
CVEs by package
Open-source packages on npm, PyPI, Maven, Go…
Critical
About
Search CVEs, products, packages and vendors
/
CVEs, without the noise
One clean record per CVE, merged from the CVE List, NVD, OSV and GitHub.
Search CVEs, products, packages and vendors
Severity
Any
Published
Last 7 days
Exploited only
Search CVEs, products, packages and vendors
Severity
Any
Published
All time
Exploited only
Clear
Results for “ggml-org llama.cpp”
Results for “ggml-org llama.cpp”
36 CVEs
CVE
Record
Severity
Status
Published
CVE-2026-27940
llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix
ggml-org llama.cpp
High
7.8
Mar 12
CVE-2026-2069
ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_grammar_advance_stack stack-based overflow
ggml-org llama.cpp
Medium
4.8
Fix available
Feb 6
CVE-2026-21869
llama.cpp has Out-of-bounds Write in llama-server
ggml-org llama.cpp
High
8.8
Jan 7
CVE-2025-53630
Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
ggml-org llama.cpp
High
8.9
Jul 10
CVE-2025-52566
llama.cpp tokenizer signed vs. unsigned heap overflow
ggml-org llama.cpp
High
8.6
Jun 24
CVE-2025-49847
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
ggml-org llama.cpp
High
8.8
Jun 17
Showing
31–36
of 36
Previous
1
2
Next