Low severity · published Feb 6, 2026
CVE-2026-2069
ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_grammar_advance_stack stack-based overflow
3.3
CVSS
0.1%
EPSS
No
On KEV
Description
A flaw has been found in ggml-org llama.cpp up to 55abc39. Impacted is the function llama_grammar_advance_stack of the file llama.cpp/src/llama-grammar.cpp of the component GBNF Grammar Handler. This manipulation causes stack-based buffer overflow. The attack needs to be launched locally. The exploit has been published and may be used. Patch name: 18993. To fix this issue, it is recommended to deploy a patch.
CVSS vector
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
Attack vector
Local
Complexity
Low
Privileges
Low
User interaction
None
Confidentiality
None
Integrity
None
Availability
Low
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.1% · higher than 4% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LL
llama.cpp · ggml-org
55abc39 · source: vendor
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-2069
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-2069
github.com
https://github.com/ggml-org/llama.cpp/
github.com
https://github.com/ggml-org/llama.cpp/issues/18988
github.com
https://github.com/ggml-org/llama.cpp/issues/18988#event-4426704865
github.com
https://github.com/ggml-org/llama.cpp/pull/18993
github.com
https://github.com/user-attachments/files/24761101/poc.zip
vuldb.com
https://vuldb.com/?ctiid.344636
More from llama.cpp
9.8
CVE-2026-34159
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
9.8
CVE-2026-21869
llama.cpp has Out-of-bounds Write in llama-server
8.9
CVE-2025-53630
Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
8.8
CVE-2025-52566
llama.cpp tokenizer signed vs. unsigned heap overflow
8.8
CVE-2025-49847
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model