Skip to content

Reject tensors with ndim > GGUF_TENSOR_MAX_DIM (fix OOB write in #25) #26

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ValheruEldarr wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Reject tensors with ndim > GGUF_TENSOR_MAX_DIM (fix OOB write in #25) #26

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion gguflib.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,7 +272,15 @@ int gguf_get_tensor(gguf_ctx *ctx, gguf_tensor *tensor) {
uint32_t *num_dim = (uint32_t*) (ctx->data+ctx->off);
ctx->off += 4; // Skip number of dimensions.
tensor->ndim = *num_dim;
assert(tensor->ndim <= GGUF_TENSOR_MAX_DIM);
/* Reject tensors declaring more dimensions than the fixed-size dim[] array
* can hold. The previous assert() is compiled out under -DNDEBUG (the usual
* release build), which left an out-of-bounds write into tensor->dim[] for
* an attacker-controlled ndim read from the file. Returning 0 cleanly stops
* iteration instead. */
if (tensor->ndim > GGUF_TENSOR_MAX_DIM) {
tensor->name = NULL;
return 0;
}

/* Read the dimentions: all the unused dimensions are set to 1. */
tensor->num_weights = 1;
Expand Down