You can deploy this model and start earning money today!

AM-Core/
gguf-invalid-kv-type-ubsan-poc

Name: gguf-invalid-kv-type-ubsan-poc
Availability: InStock

gguf

llama.cpp

model-format-vulnerability

security

ubsan

mit

Views

No views yet

llama.cpp GGUF invalid metadata type UBSan PoC

Summary

A malformed GGUF v3 file containing a key-value metadata entry with an invalid type value (0x7fffffff) triggers UndefinedBehaviorSanitizer in llama.cpp's GGUF parser.

The issue occurs in the core GGUF parsing path (gguf_init_from_file_ptr) before the invalid metadata type is rejected. The same input reaches the normal model loading path through llama-cli, not only the llama-gguf example utility.

Affected component

Project: llama.cpp
Format: GGUF
Parser path: gguf_init_from_file_ptr
File: ggml/src/gguf.cpp
Sanitizer finding: invalid enum value loaded as gguf_type

PoC file

invalid_kv_type_0x7fffffff.gguf
Size: 48 bytes
Behavior: GGUF v3 header, n_tensors=0, n_kv=1, key general.name, metadata type 0x7fffffff

Reproduction

Build llama.cpp with ASan/UBSan, then run:

bash

ASAN_OPTIONS="abort_on_error=1:detect_leaks=0:symbolize=1" \
UBSAN_OPTIONS="print_stacktrace=1:halt_on_error=1" \
./build-asan/bin/llama-gguf invalid_kv_type_0x7fffffff.gguf r n

Also reproducible through the model loading path:

bash

ASAN_OPTIONS="abort_on_error=1:detect_leaks=0:symbolize=1" \
UBSAN_OPTIONS="print_stacktrace=1:halt_on_error=1" \
./build-asan/bin/llama-cli -m invalid_kv_type_0x7fffffff.gguf -p test -n 1

Expected sanitizer signal:

text

runtime error: load of value 2147483647, which is not a valid value for type 'gguf_type'
SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior ggml/src/gguf.cpp

Normal build behavior

A non-sanitized build rejects the file cleanly with: