CVE-2025-62609
MLX has Wild Pointer Dereference in load_gguf()
MLX is an array framework for machine learning on Apple silicon. Prior to version 0.29.4, there is a segmentation fault in mlx::core::load_gguf() when loading malicious GGUF files. Untrusted pointer from external gguflib library is dereferenced without validation, causing application crash. This issue has been patched in version 0.29.4.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- None
- Integrity
- None
- Availability
- Low
Exploit likelihood
What each source reports
CVE List Score used
5.5
MLX has Wild Pointer Dereference in load_gguf()
MLX is an array framework for machine learning on Apple silicon. Prior to version 0.29.4, there is a segmentation fault in mlx::core::load_gguf() when loading malicious GGUF files. Untrusted pointer from external gguflib library is dereferenced without validation, causing application crash. This issue has been patched in version 0.29.4.
- Record
CVE-2025-62609- CVSS 4.0
- 5.5 Medium
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P - Weakness
- CWE-476
- Updated
- 2026-11-02
EUVDEUVD-2025-198500
5.5
MLX is an array framework for machine learning on Apple silicon. Prior to version 0.29.4, there is a segmentation fault in mlx::core::load_gguf() when loading malicious GGUF files. Untrusted pointer from external gguflib library is dereferenced without validation, causing application crash. This issue has been patched in version 0.29.4.
- Record
EUVD-2025-198500- CVSS 4.0
- 5.5 Medium
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-j842-xgm4-wf88
5.5
MLX has Wild Pointer Dereference in load_gguf()
Summary
Segmentation fault in mlx::core::load_gguf() when loading malicious GGUF files. Untrusted pointer from external gguflib library is dereferenced without validation, causing application crash.
Environment:
- OS: Ubuntu 20.04.6 LTS
- Compiler: Clang 19.1.7
Vulnerability
Location: mlx/io/gguf.cpp
- Function
extract_tensor_data()at lines 59-79 - Vulnerable memcpy at lines 64-67
- Called from
load_arrays()at line 177
The Bug:
std::tuple<allocator::Buffer, Dtype> extract_tensor_data(gguf_tensor* tensor) {
std::optional<Dtype> equivalent_dtype = gguf_type_to_dtype(tensor->type);
if (equivalent_dtype.has_value()) {
allocator::Buffer buffer = allocator::malloc(tensor->bsize);
memcpy(
buffer.raw_ptr(),
tensor->weights_data, // untrusted pointer from gguflib
tensor->num_weights * equivalent_dtype.value().size());
return {buffer, equivalent_dtype.value()};
}
// ...
}
Possible Fix
std::tuple<allocator::Buffer, Dtype> extract_tensor_data(gguf_tensor* tensor) {
std::optional<Dtype> equivalent_dtype = gguf_type_to_dtype(tensor->type);
if (equivalent_dtype.has_value()) {
// FIX: Validate pointer
if (!tensor->weights_data) {
throw std::runtime_error("[load_gguf] NULL tensor data pointer");
}
allocator::Buffer buffer = allocator::malloc(tensor->bsize);
memcpy(
buffer.raw_ptr(),
tensor->weights_data,
tensor->num_weights * equivalent_dtype.value().size());
return {buffer, equivalent_dtype.value()};
}
// ...
}
PoC
# Install MLX
pip install mlx
python3 -c "import mlx.core as mx; mx.load('exploit.gguf', format='gguf')"
Download the poc file there, or let me know how I can send it to you.
AddressSanitizer Output (with instrumented build):
AddressSanitizer:DEADLYSIGNAL
=================================================================
==5855==ERROR: AddressSanitizer: SEGV on unknown address 0x7fc432f64bc0 (pc 0x7fc430841c12 bp 0x7ffc04847ab0 sp 0x7ffc04847268 T0)
==5855==The signal is caused by a READ memory access.
#0 0x7fc430841c12 /build/glibc-B3wQXB/glibc-2.31/string/../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:312
#1 0x55aac829756b in __asan_memcpy (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x9ef56b) (BuildId: 57467f1ce96052757daeef4b04739be7f23c5f1f)
#2 0x55aacaa6e8dc in mlx::core::extract_tensor_data(gguf_tensor*) /home/user1/mlx/mlx/io/gguf.cpp:64:5
#3 0x55aacaa773fc in mlx::core::load_arrays[abi:cxx11](gguf_ctx*) /home/user1/mlx/mlx/io/gguf.cpp:226:35
#4 0x55aacaa782a9 in mlx::core::load_gguf(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&, std::variant<std::monostate, mlx::core::Stream, mlx::core::Device>) /home/user1/mlx/mlx/io/gguf.cpp:250:17
#5 0x55aac82dc696 in LLVMFuzzerTestOneInput /home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf.cpp:49:19
#6 0x55aac81e25c6 in fuzzer::Fuzzer::ExecuteCallback(unsigned char const*, unsigned long) (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x93a5c6) (BuildId: 57467f1ce96052757daeef4b04739be7f23c5f1f)
#7 0x55aac81cc738 in fuzzer::RunOneTest(fuzzer::Fuzzer*, char const*, unsigned long) (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x924738) (BuildId: 57467f1ce96052757daeef4b04739be7f23c5f1f)
#8 0x55aac81d220a in fuzzer::FuzzerDriver(int*, char***, int (*)(unsigned char const*, unsigned long)) (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x92a20a) (BuildId: 57467f1ce96052757daeef4b04739be7f23c5f1f)
#9 0x55aac81fbb82 in main (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x953b82) (BuildId: 57467f1ce96052757daeef4b04739be7f23c5f1f)
#10 0x7fc4307aa082 in __libc_start_main /build/glibc-B3wQXB/glibc-2.31/csu/../csu/libc-start.c:308:16
#11 0x55aac81c73ed in _start (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x91f3ed) (BuildId:…
- Record
GHSA-j842-xgm4-wf88- CVSS 4.0
- 5.5 Medium
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P - Weakness
- CWE-476
- Updated
- 2026-11-02
NVD
5.5
MLX is an array framework for machine learning on Apple silicon. Prior to version 0.29.4, there is a segmentation fault in mlx::core::load_gguf() when loading malicious GGUF files. Untrusted pointer from external gguflib library is dereferenced without validation, causing application crash. This issue has been patched in version 0.29.4.
- Record
CVE-2025-62609- CVSS 4.0
- 5.5 Medium
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/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 - CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H - Weakness
- CWE-476
- Updated
- 2026-11-02
OSV
5.5
MLX has Wild Pointer Dereference in load_gguf()
MLX is an array framework for machine learning on Apple silicon. Prior to version 0.29.4, there is a segmentation fault in mlx::core::load_gguf() when loading malicious GGUF files. Untrusted pointer from external gguflib library is dereferenced without validation, causing application crash. This issue has been patched in version 0.29.4.
- Record
CVE-2025-62609- CVSS 4.0
- 5.5 Medium
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P - Weakness
- CWE-476
- Updated
- 2026-11-02
OSVGHSA-j842-xgm4-wf88
5.5
MLX has Wild Pointer Dereference in load_gguf()
Summary
Segmentation fault in mlx::core::load_gguf() when loading malicious GGUF files. Untrusted pointer from external gguflib library is dereferenced without validation, causing application crash.
Environment:
- OS: Ubuntu 20.04.6 LTS
- Compiler: Clang 19.1.7
Vulnerability
Location: mlx/io/gguf.cpp
- Function
extract_tensor_data()at lines 59-79 - Vulnerable memcpy at lines 64-67
- Called from
load_arrays()at line 177
The Bug:
std::tuple<allocator::Buffer, Dtype> extract_tensor_data(gguf_tensor* tensor) {
std::optional<Dtype> equivalent_dtype = gguf_type_to_dtype(tensor->type);
if (equivalent_dtype.has_value()) {
allocator::Buffer buffer = allocator::malloc(tensor->bsize);
memcpy(
buffer.raw_ptr(),
tensor->weights_data, // untrusted pointer from gguflib
tensor->num_weights * equivalent_dtype.value().size());
return {buffer, equivalent_dtype.value()};
}
// ...
}
Possible Fix
std::tuple<allocator::Buffer, Dtype> extract_tensor_data(gguf_tensor* tensor) {
std::optional<Dtype> equivalent_dtype = gguf_type_to_dtype(tensor->type);
if (equivalent_dtype.has_value()) {
// FIX: Validate pointer
if (!tensor->weights_data) {
throw std::runtime_error("[load_gguf] NULL tensor data pointer");
}
allocator::Buffer buffer = allocator::malloc(tensor->bsize);
memcpy(
buffer.raw_ptr(),
tensor->weights_data,
tensor->num_weights * equivalent_dtype.value().size());
return {buffer, equivalent_dtype.value()};
}
// ...
}
PoC
# Install MLX
pip install mlx
python3 -c "import mlx.core as mx; mx.load('exploit.gguf', format='gguf')"
Download the poc file there, or let me know how I can send it to you.
AddressSanitizer Output (with instrumented build):
AddressSanitizer:DEADLYSIGNAL
=================================================================
==5855==ERROR: AddressSanitizer: SEGV on unknown address 0x7fc432f64bc0 (pc 0x7fc430841c12 bp 0x7ffc04847ab0 sp 0x7ffc04847268 T0)
==5855==The signal is caused by a READ memory access.
#0 0x7fc430841c12 /build/glibc-B3wQXB/glibc-2.31/string/../sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S:312
#1 0x55aac829756b in __asan_memcpy (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x9ef56b) (BuildId: 57467f1ce96052757daeef4b04739be7f23c5f1f)
#2 0x55aacaa6e8dc in mlx::core::extract_tensor_data(gguf_tensor*) /home/user1/mlx/mlx/io/gguf.cpp:64:5
#3 0x55aacaa773fc in mlx::core::load_arrays[abi:cxx11](gguf_ctx*) /home/user1/mlx/mlx/io/gguf.cpp:226:35
#4 0x55aacaa782a9 in mlx::core::load_gguf(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char>> const&, std::variant<std::monostate, mlx::core::Stream, mlx::core::Device>) /home/user1/mlx/mlx/io/gguf.cpp:250:17
#5 0x55aac82dc696 in LLVMFuzzerTestOneInput /home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf.cpp:49:19
#6 0x55aac81e25c6 in fuzzer::Fuzzer::ExecuteCallback(unsigned char const*, unsigned long) (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x93a5c6) (BuildId: 57467f1ce96052757daeef4b04739be7f23c5f1f)
#7 0x55aac81cc738 in fuzzer::RunOneTest(fuzzer::Fuzzer*, char const*, unsigned long) (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x924738) (BuildId: 57467f1ce96052757daeef4b04739be7f23c5f1f)
#8 0x55aac81d220a in fuzzer::FuzzerDriver(int*, char***, int (*)(unsigned char const*, unsigned long)) (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x92a20a) (BuildId: 57467f1ce96052757daeef4b04739be7f23c5f1f)
#9 0x55aac81fbb82 in main (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x953b82) (BuildId: 57467f1ce96052757daeef4b04739be7f23c5f1f)
#10 0x7fc4307aa082 in __libc_start_main /build/glibc-B3wQXB/glibc-2.31/csu/../csu/libc-start.c:308:16
#11 0x55aac81c73ed in _start (/home/user1/mlx/fuzz/load_gguf/fuzz_load_gguf+0x91f3ed) (BuildId:…
- Record
GHSA-j842-xgm4-wf88- CVSS 4.0
- 5.5 Medium
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P - Weakness
- CWE-476
- Updated
- 2026-11-02
OSVPYSEC-2025-139
7.5
MLX is an array framework for machine learning on Apple silicon. Prior to version 0.29.4, there is a segmentation fault in mlx::core::load_gguf() when loading malicious GGUF files. Untrusted pointer from external gguflib library is dereferenced without validation, causing application crash. This issue has been patched in version 0.29.4.
- Record
PYSEC-2025-139- CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H - Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
mlxPyPI |
through 0.29.3 | 0.29.4 |
mlxPyPI |
before 0.29.4, plus listed versions 0.0.100.0.110.0.20.0.30.0.4 Show 40 moreShow less0.0.50.0.60.0.70.0.90.1.00.10.00.11.10.12.20.13.00.13.10.14.10.15.20.16.30.17.30.18.10.19.30.2.00.20.00.21.10.22.10.23.20.24.20.25.20.26.10.26.20.26.30.26.50.27.10.28.00.29.00.29.10.29.20.29.30.3.00.4.00.5.10.6.00.7.00.8.10.9.1 |
0.29.4 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2025-62609 is a medium vulnerability (CVSS 5.5) in Ml-explore Mlx, published November 21, 2025. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.40%, the 34th percentile. Fixed in mlx 0.29.4.
References
github.com/ml-explore/mlx/security/advisories/GHSA-j842-xgm4-wf88
nvd.nist.gov/vuln/detail/CVE-2025-62609
github.com/pypa/advisory-database/tree/main/vulns/mlx/PYSEC-2025-139.yaml
github.com/advisories/GHSA-j842-xgm4-wf88
github.com/CVEProject/cvelistV5/tree/main/cves/2025/62xxx/CVE-2025-62609.json
github.com/ml-explore/mlx
Left out here: the rest of 2 source descriptions. The JSON record has them.