Skip to content
Fencer Intel
low 3.3

CVE-2026-2069 json

ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_grammar_advance_stack stack-based overflow

published 9mo ago modified 4mo ago also EUVD-2026-5558

cvss
3.3
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.1%
EPSS 0.1% chance of exploitation in 30 days, percentile 4%
public exploits
0
none known

Summary

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.

Patch / fix

Is CVE-2026-2069 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-2069 updated cvss 5.5

llama.cpp: infinite recursion in GBNF grammar via nested repetition

  • Red Hat All currently supported Red Hat products
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
partial
Assessed
8mo ago

Exploit prediction

0.15% chance of exploitation in the next 30 days, higher than 4% of all scored CVEs (FIRST EPSS, 2026-11-09).

Exploits and checks

  • github.com https://github.com/user-attachments/files/24761101/poc.zip referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 4.0 4.8 CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P
CNA 3.1 3.3 CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L/E:P/RL:O/RC:C
CNA 3.0 3.3 CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L/E:P/RL:O/RC:C
CNA 2.0 1.7 AV:L/AC:L/Au:S/C:N/I:N/A:P/E:POC/RL:OF/RC:C
CNA 4.0 1.9 CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CNA 3.1 3.3 CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
CNA 2.0 1.7 AV:L/AC:L/Au:S/C:N/I:N/A:P

Affected products

  • ggml-org llama.cpp

Classification

Weakness
  • CWE-121 Stack-based Buffer Overflow
  • CWE-119 Improper Restriction of Operations within the Bounds of a Memory Buffer

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.