// For flags

CVE-2025-53630

Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf

Severity Score

8.9
*CVSS v4

Exploit Likelihood

*EPSS

Affected Versions

*CPE

Public Exploits

0
*Multiple Sources

Exploited in Wild

-
*KEV

Decision

Track*
*SSVC
Descriptions

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.

*Credits: N/A
CVSS Scores
Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
None
System
Vulnerable | Subsequent
Confidentiality
High
None
Integrity
High
None
Availability
High
None
Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
Required
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High
Attack Vector
Network
Attack Complexity
Medium
Authentication
None
Confidentiality
Partial
Integrity
Partial
Availability
Partial
* Common Vulnerability Scoring System
SSVC
  • Decision:Track*
Exploitation
Poc
Automatable
No
Tech. Impact
Partial
* Organization's Worst-case Scenario
Timeline
  • 2025-07-07 CVE Reserved
  • 2025-07-10 CVE Published
  • 2025-07-10 CVE Updated
  • 2025-07-16 EPSS Updated
  • ---------- Exploited in Wild
  • ---------- KEV Due Date
  • ---------- First Exploit
CWE
  • CWE-122: Heap-based Buffer Overflow
  • CWE-680: Integer Overflow to Buffer Overflow
CAPEC
Affected Vendors, Products, and Versions
Vendor Product Version Other Status
Vendor Product Version Other Status <-- --> Vendor Product Version Other Status
Ggml-org
Search vendor "Ggml-org"
 Llama.cpp
Search vendor "Ggml-org" for product "Llama.cpp"
 < 26
Search vendor "Ggml-org" for product "Llama.cpp" and version " < 26"
en
Affected