openssl enc -rc4 is broken proof code

/*
    PoC application showing openssl enc -rc4 -K <8byte_key_hd> is broken
    128-bit key HD is 0123456789abcdef

    # this file: rc4.c
    $ gcc -o rc4_polarssl rc4.c
    $ gcc -o rc4_openssl rc4.c -lcrypto -DOPENSSL
    $ head -c 8 /dev/zero | openssl enc -rc4 -K 0123456789abcdef | hexdump -C
    00000000  68 51 73 3e 92 f9 8f 5e                           |hQs>...^|
    00000008
    $ head -c 8 /dev/zero | ./rc4_polarssl | hexdump -C
    00000000  74 94 c2 e7 10 4b 08 79                           |t....K.y|
    00000008
    $ head -c 8 /dev/zero | ./rc4_openssl | hexdump -C
    00000000  74 94 c2 e7 10 4b 08 79                           |t....K.y|
    00000008
    $
    # the above result of crypting 8 zero-bytes with key 0123456789abcdef (128 bit/8 bytes) matches proposed polarssl test vector.
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>

#ifdef OPENSSL
#include <openssl/rc4.h>
#endif

#ifndef OPENSSL
typedef struct
{
    int x;                      /*!< permutation index */
    int y;                      /*!< permutation index */
    unsigned char m[256];       /*!< permutation table */
} arc4_context;

void arc4_setup( arc4_context *ctx, const unsigned char *key, unsigned int keylen );
void arc4_crypt( arc4_context *ctx, size_t length, const unsigned char *input,unsigned char *output );
int arc4_self_test( int verbose );
#endif

int main() {
    unsigned char * in =  alloca(4096);
    unsigned char * out = alloca(4096);
    int rr;
#ifndef OPENSSL
    arc4_context ctx;
#else
    RC4_KEY k;
#endif

    //arc4_self_test(1);

    //arc4_setup(&ctx,"\x38\xe6\x89\x75\x49\x52\x5e\x82",8);
#ifndef OPENSSL
    arc4_setup(&ctx,"\x01\x23\x45\x67\x89\xab\xcd\xef",8);
#else
    RC4_set_key(&k,8,"\x01\x23\x45\x67\x89\xab\xcd\xef");
#endif

    while ( 0 < ( rr = read(0,in,4096) ) ) {
#ifndef OPENSSL
        arc4_crypt(&ctx,rr,in,out);
#else
        RC4(&k,rr,in,out);
#endif
        if ( rr != write(1,out,rr) )
            return 1;
    }
    return 0;
}

#ifndef OPENSSL
static const unsigned char arc4_test_key[3][8] =
{
    { 0x01, 0x23, 0x45, 0x67, 0x89, 0xAB, 0xCD, 0xEF },
    { 0x01, 0x23, 0x45, 0x67, 0x89, 0xAB, 0xCD, 0xEF },
    { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }
};

static const unsigned char arc4_test_pt[3][8] =
{
    { 0x01, 0x23, 0x45, 0x67, 0x89, 0xAB, 0xCD, 0xEF },
    { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 },
    { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }
};

static const unsigned char arc4_test_ct[3][8] =
{
    { 0x75, 0xB7, 0x87, 0x80, 0x99, 0xE0, 0xC5, 0x96 },
    { 0x74, 0x94, 0xC2, 0xE7, 0x10, 0x4B, 0x08, 0x79 },
    { 0xDE, 0x18, 0x89, 0x41, 0xA3, 0x37, 0x5D, 0x3A }
};

int arc4_self_test( int verbose )
{
    int i;
    unsigned char ibuf[8];
    unsigned char obuf[8];
    arc4_context ctx;

    for( i = 0; i < 3; i++ )
    {
        if( verbose != 0 )
            printf( "  ARC4 test #%d: ", i + 1 );

        memcpy( ibuf, arc4_test_pt[i], 8 );

        arc4_setup( &ctx, (unsigned char *) arc4_test_key[i], 8 );
        arc4_crypt( &ctx, 8, ibuf, obuf );

        if( memcmp( obuf, arc4_test_ct[i], 8 ) != 0 )
        {
            if( verbose != 0 )
                printf( "failed\n" );

            return( 1 );
        }

        if( verbose != 0 )
            printf( "passed\n" );
    }

    if( verbose != 0 )
        printf( "\n" );

    return( 0 );
}

void arc4_setup( arc4_context *ctx, const unsigned char *key, unsigned int keylen )
{
    int i, j, a;
    unsigned int k;
    unsigned char *m;

    ctx->x = 0;
    ctx->y = 0;
    m = ctx->m;

    for( i = 0; i < 256; i++ )
        m[i] = (unsigned char) i;

    j = k = 0;

    for( i = 0; i < 256; i++, k++ )
    {
        if( k >= keylen ) k = 0;

        a = m[i];
        j = ( j + a + key[k] ) & 0xFF;
        m[i] = m[j];
        m[j] = (unsigned char) a;
    }
}

void arc4_crypt( arc4_context *ctx, size_t length, const unsigned char *input,
                unsigned char *output )
{
    int x, y, a, b;
    size_t i;
    unsigned char *m;

    x = ctx->x;
    y = ctx->y;
    m = ctx->m;

    for( i = 0; i < length; i++ )
    {
        x = ( x + 1 ) & 0xFF; a = m[x];
        y = ( y + a ) & 0xFF; b = m[y];

        m[x] = (unsigned char) b;
        m[y] = (unsigned char) a;

        output[i] = (unsigned char)
            ( input[i] ^ m[(unsigned char)( a + b )] );
    }

    ctx->x = x;
    ctx->y = y;
}

#endif