8.5

CVE-2026-133710: llama.cpp b11003 before b12556 Heap Out-of-Bounds Write via hrm_text Model Loader

Awaiting analysis
Published 20-11-2026Last modified 20-11-2026

Vulnerability summary

CVE-2026-133710 is a high (CVSS 8.5) Integer Overflow or Wraparound vulnerability in ggml-org llama.cpp.

Priority
Routine

Not severe (CVSS 8.5, local access); no exploitation reported by the 5 checked sources

Source freshness unavailable

How is this decided?
CVSS score
8.5/10
010
High · v4.0 (CVE.org)
EPSS scoreNot scoredRisk metrics not yet published.
KEVNot listedNot listed by any tracked catalog.
RansomwareNot flaggedNo ransomware use recorded.
Public exploits0No public exploits recorded

Timeline

  1. 20-11-2026
    PublishedVulnerability first disclosed.
  2. 20-11-2026
    Last modifiedVulnerability information updated.

Description

llama.cpp b11003 before b12556 contains an integer overflow in the hrm_text loader load_arch_hparams() that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing load_arch_tensors() to write tensor pointers past model.layers, corrupting heap memory and potentially enabling code execution.

CVSS metrics

4 scores · 2 sources · 2 versions

EPSS trend

No EPSS score has been published for this record yet.

Known exploited

Compare KEV catalogs
CISA KEV

Not in the CISA KEV catalog.

ENISA CNW

Not in the ENISA CNW catalog.

CIRCL

Not in the CIRCL catalog.

Public exploits

0 found

No public exploits indexed.

Weaknesses

CWE · root cause

Affected systems

Version check

Known conditions: local access, no authentication, user interaction (CVSS vector). Other conditions: not stated in public data.

Ggml-org1 product

1 vendor · 1 product

References

5 links