7efe8bbfbf
Security Fixes: - CVE-2024-45339: Add O_EXCL flag to temp file creation in storage_write_entries() Prevents symlink attacks on predictable .tmp file paths - CVE-2025-47290: Use openat_nofollow() in storage_open() Closes TOCTOU race condition via path_sanitizer infrastructure - CVE-2025-0838: Add MAX_BATCH_SIZE=10000 to add_tasks() Prevents integer overflow in batch operations Research Trustworthiness (dataset_hash): - Deterministic file ordering: std::sort after collect_files() - Recursive directory traversal: depth-limited with cycle detection - Documented exclusions: hidden files and special files noted in API Bug Fixes: - R1: storage_init path validation for non-existent directories - R2: safe_strncpy return value check before strcat - R3: parallel_hash 256-file cap replaced with std::vector - R4: wire qi_compact_index/qi_rebuild_index stubs - R5: CompletionLatch race condition fix (hold mutex during decrement) - R6: ARMv8 SHA256 transform fix (save abcd_pre before vsha256hq_u32) - R7: fuzz_index_storage header format fix - R8: enforce null termination in add_tasks/update_tasks - R9: use 64 bytes (not 65) in combined hash to exclude null terminator - R10: status field persistence in save() New Tests: - test_recursive_dataset.cpp: Verify deterministic recursive hashing - test_storage_symlink_resistance.cpp: Verify CVE-2024-45339 fix - test_queue_index_batch_limit.cpp: Verify CVE-2025-0838 fix - test_sha256_arm_kat.cpp: ARMv8 known-answer tests - test_storage_init_new_dir.cpp: F1 verification - test_parallel_hash_large_dir.cpp: F3 verification - test_queue_index_compact.cpp: F4 verification All 8 native tests passing. Library ready for research lab deployment.
49 lines
1.2 KiB
C++
49 lines
1.2 KiB
C++
// fuzz_file_hash.cpp - libFuzzer harness for file hashing
|
|
// Tests hash_file with arbitrary file content
|
|
|
|
#include <cstdint>
|
|
#include <cstddef>
|
|
#include <cstdio>
|
|
#include <cstring>
|
|
#include <unistd.h>
|
|
#include <fcntl.h>
|
|
|
|
// Include the file hash implementation
|
|
#include "../../dataset_hash/io/file_hash.h"
|
|
|
|
extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size) {
|
|
// Create a temporary file
|
|
char tmpfile[] = "/tmp/fuzz_hash_XXXXXX";
|
|
int fd = mkstemp(tmpfile);
|
|
if (fd < 0) {
|
|
return 0;
|
|
}
|
|
|
|
// Write fuzz data
|
|
write(fd, data, size);
|
|
close(fd);
|
|
|
|
// Try to hash the file
|
|
char hash[65];
|
|
int result = hash_file(tmpfile, 64 * 1024, hash);
|
|
|
|
// Verify: if success, hash must be 64 hex chars
|
|
if (result == 0) {
|
|
// Check all characters are valid hex
|
|
for (int i = 0; i < 64; i++) {
|
|
char c = hash[i];
|
|
if (!((c >= '0' && c <= '9') || (c >= 'a' && c <= 'f'))) {
|
|
__builtin_trap(); // Invalid hash format
|
|
}
|
|
}
|
|
// Must be null-terminated at position 64
|
|
if (hash[64] != '\0') {
|
|
__builtin_trap();
|
|
}
|
|
}
|
|
|
|
// Cleanup
|
|
unlink(tmpfile);
|
|
|
|
return 0; // Non-crashing input
|
|
}
|