Misaligned `uint32_t` load in `sha1_compression_states` when hashing a git object whose header length is not a multiple of 4

$ git describe --tags
v1.9.0-429-g32b564e63

// sha1.c:1819-1856 (abridged)
void SHA1DCUpdate(SHA1_CTX *ctx, const char *buf, size_t len)
{
    unsigned left, fill;
    if (len == 0) return;
    left = ctx->total & 63;
    fill = 64 - left;

    if (left && len >= fill) {
        ctx->total += fill;
        memcpy(ctx->buffer + left, buf, fill);          // safe: into aligned buffer
        sha1_process(ctx, (uint32_t*)(ctx->buffer));    // safe: ctx->buffer is aligned
        buf += fill;                                    // <-- buf advances by `fill`
        len -= fill;
        left = 0;
    }
    while (len >= 64)
    {
        ctx->total += 64;
#if defined(SHA1DC_ALLOW_UNALIGNED_ACCESS)
        sha1_process(ctx, (uint32_t*)(buf));            // <-- CRASH: buf may be misaligned
#else
        memcpy(ctx->buffer, buf, 64);                   // safe path (dead on x86)
        sha1_process(ctx, (uint32_t*)(ctx->buffer));
#endif
        buf += 64;
        len -= 64;
    }
    ...
}

// src/util/hash.c:118-142 (abridged)
int git_hash_vec(unsigned char *out, git_str_vec *vec, size_t n, git_hash_algorithm_t algorithm)
{
    git_hash_ctx ctx;
    ...
    for (i = 0; i < n; i++) {
        if ((error = git_hash_update(&ctx, vec[i].data, vec[i].len)) < 0)   // header, then data
            goto done;
    }
    ...
}

// src/libgit2/odb.c:86-106 (abridged)
int git_odb__format_object_header(size_t *written, char *hdr, size_t hdr_size,
                                  git_object_size_t obj_len, git_object_t obj_type)
{
    const char *type_str = git_object_type2string(obj_type);   // "blob"
    ...
    len = p_snprintf(hdr, hdr_max, "%s %"PRId64, type_str, (int64_t)obj_len);
    *written = (size_t)(len + 1);   // includes the trailing NUL
    ...
}

#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <vector>
#include "git2.h"

/*
 * Object data length. The resulting header is "blob 128\0" = 9 bytes.
 * 9 % 4 = 1, so the header length is not a multiple of 4. After SHA1DCUpdate
 * processes the 9-byte header, the data vector's fill offset is
 * 64 - 9 = 55 (55 % 4 = 3), leaving the data pointer misaligned for uint32_t.
 * 128 - 55 = 73 >= 64, so the misaligned sha1_process() loop is entered.
 */
static const size_t OBJ_LEN = 128;

int main(void)
{
    if (git_libgit2_init() < 0) {
        fprintf(stderr, "git_libgit2_init failed\n");
        return 1;
    }

    /* std::vector data is max_align_t-aligned (16 on x86-64), so the base
     * is 4-byte aligned; only the internal fill offset makes it misaligned. */
    std::vector<unsigned char> data(OBJ_LEN, 'A');

    /* Public API. opts zeroed by GIT_OBJECT_ID_OPTIONS_INIT;
     * object_type left 0 -> normalize_options() defaults it to GIT_OBJECT_BLOB,
     * oid_type left 0 -> defaults to GIT_OID_DEFAULT (SHA1). */
    git_object_id_options opts = GIT_OBJECT_ID_OPTIONS_INIT;
    opts.object_type = GIT_OBJECT_BLOB;

    git_oid oid;
    /* Hashes a blob. Triggers the misaligned load inside SHA1DC. */
    int rc = git_object_id_from_buffer(&oid, data.data(), data.size(), &opts);

    printf("git_object_id_from_buffer returned %d\n", rc);

    git_libgit2_shutdown();
    return 0;
}

src/util/hash/sha1dc/sha1.c:391:2: runtime error: load of misaligned address 0x775d233e0077 for type 'const uint32_t' (aka 'const unsigned int'), which requires 4 byte alignment
0x775d233e0077: note: pointer points here
 41 41 41 41 41  41 41 41 41 41 41 41 41  41 41 41 41 41 41 41 41  41 41 41 41 41 41 41 41  41 41 41
             ^ 
    #0 0x6482555b08e2 in sha1_compression_states src/util/hash/sha1dc/sha1.c:391:2
    #1 0x6482555b1cc4 in sha1_process src/util/hash/sha1dc/sha1.c:1725:2
    #2 0x6482555b1611 in SHA1DCUpdate src/util/hash/sha1dc/sha1.c:1843:3
    #3 0x64825558e719 in git_hash_sha1_update src/util/hash/collisiondetect.c:35:2
    #4 0x6482555563b8 in git_hash_update src/util/hash.c:72:10
    #5 0x648255556a25 in git_hash_vec src/util/hash.c:132:16
    #6 0x6482553d112b in id_from_buffer src/libgit2/object.c:875:9
    #7 0x6482553ccd81 in git_object_id_from_buffer src/libgit2/object.c:902:10
    #8 0x6482553b9865 in main poc.cpp:36:14
    #9 0x7a9d240021c9 in __libc_start_call_main csu/../sysdeps/nptl/libc_start_call_main.h:58:16
    #10 0x7a9d2400228a in __libc_start_main csu/../csu/libc-start.c:360:3
    #11 0x6482552ce6f4 in _start (poc+0x3eb6f4) (BuildId: a72440934c9e1f00dcd374ca91386c810be789ee)

SUMMARY: UndefinedBehaviorSanitizer: undefined-behavior src/util/hash/sha1dc/sha1.c:391:2 

# 1. Checkout libgit2 at the version above
git clone https://github.com/libgit2/libgit2.git
cd libgit2
git checkout 32b564e63f9639eaf5ee90fb7a95b3a650156cbd

# 2. Build the library with ASan+UBSan
SAN_FLAGS="-fsanitize=address,undefined -fno-omit-frame-pointer -ftrivial-auto-var-init=zero -g -O0 -DSHA1DC_FORCE_UNALIGNED_ACCESS"
CC=/usr/bin/clang CXX=/usr/bin/clang++ \
CFLAGS="$SAN_FLAGS" CXXFLAGS="$SAN_FLAGS" LDFLAGS="-fsanitize=address,undefined" \
cmake -S . -B build_san \
  -DBUILD_TESTS=OFF -DBUILD_FUZZERS=OFF -DBUILD_SHARED_LIBS=OFF \
  -DBUILD_CLAR=OFF -DCMAKE_BUILD_TYPE=Debug \
  -DUSE_SSH=OFF -DUSE_HTTPS=SecureTransport -DUSE_HTTP_PARSER=builtin \
  -DREGEX_BACKEND=builtin -DUSE_BUNDLED_ZLIB=ON
cmake --build build_san -j

# 3. Build the standalone PoC against the sanitizer build
clang++ -g -O0 -fstandalone-debug -fno-omit-frame-pointer \
    -ftrivial-auto-var-init=zero -fsanitize=address,undefined,fuzzer-no-link \
    -Ibuild_san/include poc.cpp -o poc \
    build_san/libgit2.a \
    -framework CoreFoundation -framework Security -framework GSS -lz -liconv

# 4. Run
ASAN_OPTIONS=detect_leaks=0 UBSAN_OPTIONS=print_stacktrace=1:halt_on_error=0 ./poc