Update README.md

README.md

@@ -10,9 +10,9 @@ model_format: gguf
 security_scan: intentionally-malformed
 ---
 
-# Load-Time Division-by-Zero DoS in llama.cpp GGUF Metadata Parser
+# Load-Time Division-by-Zero Crash in llama.cpp GGUF Metadata Parser
 
-⚠️ This repository does **not** contain a machine learning model.  
+⚠️ **This repository does not contain a machine learning model.**  
 The file provided is intentionally malformed and exists solely for security research and vulnerability reproduction.
 
 ## PoC Artifact
@@ -25,8 +25,9 @@ The file provided is intentionally malformed and exists solely for security rese
 
 ## Vulnerability Summary
 
-A malformed GGUF file can trigger a deterministic crash during model loading due to a division-by-zero condition in GGUF tensor shape validation.  
-The crash occurs at load time, before inference or tensor data processing.
+A malformed GGUF file can trigger a deterministic crash during model loading due to a division-by-zero condition in GGUF tensor shape validation.
+
+The crash occurs at **load time**, before inference or tensor data processing, and results in immediate process termination.
 
 ## Reproduction
 
@@ -35,9 +36,3 @@ From a `llama.cpp` build directory:
 ```bash
 ./llama-gguf poc_fp_exception.gguf r
 ```
-
-## Expected Result
-
-The process terminates during GGUF parsing with a fatal runtime error
-(division by zero). This occurs deterministically during model load and
-does not require any non-default configuration.