简单版WAF代码学习
网上代码只见了http://sourceforge.net/projects/sqlxsswaf/?source=directory
开始read!
一: 主函数
流程很清晰,
1. 整个WAF主函数体为死循环,在while(1)的代码段中,当代码处理完毕当前日志内容后,睡眠10ms,继续从get_pos处向后处理新内容。
2. 第二个while处理日志,当找到get或post为开头的日志内容后,对客户端发送来的命令进行检测,直到文档结尾。然后到达1中while循环的末尾
#define tailer "/var/log/apache2/access.log"
#define finder "GET"
#define finder2 "POST"
int main(void){
fpos_t get_pos;
printf("SQLXSSGRABBER HAS STARTED\n");
while(1) {
FILE *fp = fopen(tailer,"r");
fsetpos(fp,&get_pos);
if (fp != NULL){
char max_line[LINE_MAX];
while(fgets(max_line,sizeof(max_line),fp) != NULL)
{
if (strstr(max_line,finder)||strstr(max_line,finder2)){
fgetpos(fp,&get_pos);
capture(max_line);
}
}
fclose(fp);
}
else{
perror(tailer);
}
sleep(10);
}
return 0;
}
二: capture函数
主要是一个中间层,把具体的正则式和匹配实现抽象成一个函数,供main使用。
很新奇的一点是,全部case使用了FALL THROUTH,又从regex_roller开始控制,很方便,省去了许多修改功能的注释时间,不需要某个引擎又不想要删除的时候,直接放在regex_roller的前面即可。
#define att_1 "((\%3C)|<)[^\n]+((\%3E)|>)"
#define att_2 "((\%3C)|<)((\%2F)|\\/)*[a-z0-9\%]+((\%3E)|>)"
#define att_3 "((\%3C)|<)((\%69)|i|(\%49))((\%6D)|m|(\%4D))((\%67)|g|(\%47))[^\n]+((\%3E)|>)"
#define att_4 "((\%27)|('))union"
#define att_5 "((\%3D)|(=))[^\n]*((\%27)|(\\')|(\\-\\-)|(\%3B)|(;))"
#define att_6 "((\%27)|('))"
char *capture(char *log_line){
int regex_roller =0;
char *xss_para_regex = att_1;
char *xss_simple_regex = att_2;
char *css_img_regex = att_3;
char *unionsql_regex = att_4;
char *sqlmeta_regex = att_5;
char *sqlmagicquote_regex = att_6;
switch(regex_roller){
//add as many more as you wish but dont forget to #define the regex above.
case 0:
cap_matcher(log_line,xss_para_regex,0);
case 1:
cap_matcher(log_line,xss_simple_regex,1);
case 2:
cap_matcher(log_line,css_img_regex,2);
case 3:
cap_matcher(log_line,unionsql_regex,3);
case 4:
cap_matcher(log_line,sqlmeta_regex,4);
case 5:
cap_matcher(log_line,sqlmagicquote_regex,5);
default:
break;
}
return 0;
}
方便带来的后果就是如果检测出一段攻击代码后,会对这段代码继续进行其他可能性的检测,这是不需要的,同时底层函数功能过于复杂,把本该在中间层函数实现的功能带到了底层去。
三: 匹配引擎
首先编译正则式,然后进行匹配,匹配成功,根据传入的规则编号,输出对应的攻击方式,阻塞IP,再利用邮件通知给管理员。
char *cap_matcher(char *log_line, char *regex,int attack_type){
pid_t pid;
pcre *attack_regex;
const char *error;
int erroffset;
int ovector[OVECCOUNT];
int rc;
attack_regex = pcre_compile(regex,0,&error,&erroffset,NULL);
if (! attack_regex){
fprintf(stderr,"PCRE compilation failed at expression offset %d: %s\n", erroffset, error);
return (char *)1;
}
rc = pcre_exec(attack_regex,NULL,log_line,strlen(log_line),0,0,ovector,OVECCOUNT);
if (rc < 3)
{
return (char *)1;
}
else{
switch(attack_type){
case 0:
printf("Paranoid Xss Filter Detection\n");
iptables_blockage(log_line);
break;
case 1:
printf("Simple Xss Filter Detection\n");
iptables_blockage(log_line);
break;
case 2:
printf("Xss Img Filter Detection\n");
iptables_blockage(log_line);
break;
case 3:
printf("Sql Injection Union Filter Detection\n");
iptables_blockage(log_line);
break;
case 4:
printf("Sql Injection meta characters Filter Detection\n");
iptables_blockage(log_line);
break;
case 5:
printf("Sql Injection magic quote Filter Detection\n");
iptables_blockage(log_line);
break;
default:
break;
}
pid = fork();
if (pid ==0){
FILE *emails = popen("/usr/bin/mail -s 'WebAttack On server' root@localhost","w");
fprintf(emails,"Attack FOUND %s ! in the log file.\n",log_line);
pclose(emails);
_exit(0);
}
}
return 0;
}
个人感觉作者在这里的代码逻辑有些混乱,应该在匹配成功后,结束代码,返回中间层的capture函数进行处理,在capture中用宏来替换代码
这样代码会少很多而且逻辑清晰:)
#define R(re,way,info) if(cap_matcher(log_line,#re,#way)){\
printf(##info);\
iptables_blockage(log_line);\
break;\
}
四: 防火墙阻塞IP
apache的log文件如下格式:
127.0.0.1 - - [23/Sep/2011:15:27:36 +0800] "GET / HTTP/1.1" 200 44
因此以第一个空格为标准,获取IP后,调用iptables添加阻塞IP
void iptables_blockage(char *log_line){
char *ip_address= malloc(100);
char command[1000];
int i;
for (i =0; i <= 100 ; i++){
if (isspace(log_line[i])){break;}
ip_address[i] = log_line[i];
}
snprintf(command,sizeof(command),"/sbin/iptables -A INPUT -s %s -j DROP",ip_address);
FILE *iptables_run = (FILE*)popen(command,"r");
pclose(iptables_run);
free(ip_address);
}
最后的邮件通知实现与iptables差不多,详细的可以参见前一篇文章,LINUX下C语言利用命令发邮件

浙公网安备 33010602011771号