fix: rewrite all filters for current NPM log format

NPM changed its log format. Old filters expected classic nginx format:
  PROXY_IP - - [date] "METHOD PATH" STATUS BYTES "REF" "UA" [Client IP]

Actual current format:
  [date] - STATUS STATUS - METHOD SCHEME HOST "PATH" [Client IP] [Length N] [Gzip N] [Sent-to IP] "UA" "REFERER"

fail2ban strips the timestamp before applying failregex, so patterns
must match the post-strip line (no ^ timestamp prefix).

All three filters updated: http-errors, npm-probe, badbot.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-02-20 18:02:51 +00:00
parent fee62b303f
commit 572e8bbe4e
3 changed files with 30 additions and 14 deletions

View File

@@ -1,15 +1,18 @@
[Definition]
# ── NPM access log format ─────────────────────────────────────────────────────
# PROXY_IP - - [DD/Mon/YYYY:HH:MM:SS +0000] "METHOD PATH HTTP/VER" STATUS BYTES "REFERER" "UA" [Client REAL_IP]
# ── NPM access log format (current) ──────────────────────────────────────────
# [DD/Mon/YYYY:HH:MM:SS +0000] - STATUS STATUS - METHOD SCHEME HOST "PATH"
# [Client REAL_IP] [Length N] [Gzip N] [Sent-to IP] "UA" "REFERER"
#
# <HOST> is placed at the [Client REAL_IP] position — this is the IP that gets
# banned, which is the real client IP forwarded by Cloudflare/CDN via X-Forwarded-For.
# fail2ban strips the timestamp before applying failregex, leaving:
# " - STATUS STATUS - METHOD SCHEME HOST "PATH" [Client IP] ... "UA" ..."
#
# UA appears after [Sent-to ...] so .* is used between <HOST> and the UA match.
#
# Test against your logs:
# fail2ban-regex /nginx-logs/proxy-host-1_access.log /etc/fail2ban/filter.d/badbot.conf
# ─────────────────────────────────────────────────────────────────────────────
failregex = ^\S+ - - \[[^\]]+\] "\S+ [^"]*" \d{3} \d+ "[^"]*" "(?i:masscan|zgrab|python-requests|go-http-client/1\.1|nuclei|sqlmap|dirbuster|gobuster|nikto|wfuzz|metasploit|libwww-perl|wpscan|nmap|zmeu|jorgee|shodan\.com|censys|binaryedge|internet-measurement|netcraft|strikeready|dataforseo|semrushbot|ahrefsbot|mj12bot|dotbot)[^"]*" \[Client <HOST>\]
failregex = - \d+ \d+ - \S+ \S+ \S+ "[^"]*" \[Client <HOST>\].*"(?i:masscan|zgrab|python-requests|go-http-client/1\.1|nuclei|sqlmap|dirbuster|gobuster|nikto|wfuzz|metasploit|libwww-perl|wpscan|nmap|zmeu|jorgee|shodan\.com|censys|binaryedge|internet-measurement|netcraft|strikeready|dataforseo|semrushbot|ahrefsbot|mj12bot|dotbot)[^"]*"
ignoreregex =

View File

@@ -1,14 +1,20 @@
[Definition]
# ── NPM access log format ─────────────────────────────────────────────────────
# ── NPM access log format (current) ──────────────────────────────────────────
# [DD/Mon/YYYY:HH:MM:SS +0000] - STATUS STATUS - METHOD SCHEME HOST "PATH"
# [Client REAL_IP] [Length N] [Gzip N] [Sent-to IP] "UA" "REFERER"
#
# fail2ban strips the timestamp before applying failregex, leaving:
# " - STATUS STATUS - METHOD SCHEME HOST "PATH" [Client IP] ..."
#
# Bans IPs generating excessive 4xx/5xx errors.
# Default jail: 15 errors in 5 minutes (tunable in jail.local).
#
# PROXY_IP - - [date] "METHOD PATH HTTP/VER" STATUS BYTES "REFERER" "UA" [Client REAL_IP]
# Test against your logs:
# fail2ban-regex /nginx-logs/proxy-host-1_access.log /etc/fail2ban/filter.d/http-errors.conf
# ─────────────────────────────────────────────────────────────────────────────
failregex = ^\S+ - - \[[^\]]+\] "\S+ [^"]*" [45]\d\d \d+ "[^"]*" "[^"]*" \[Client <HOST>\]
failregex = - [45]\d\d \d+ - \S+ \S+ \S+ "[^"]*" \[Client <HOST>\]
# Exclude very common benign 404s to reduce noise.
# Remove these if you want to count ALL error responses.
ignoreregex = ^\S+ - - \[[^\]]+\] "\S+ /(?:favicon\.ico|robots\.txt|sitemap\.xml|apple-touch-icon[^"]*|\.well-known/[^"]*)[^"]*" 404 \d+ "[^"]*" "[^"]*" \[Client <HOST>\]
# Exclude common benign 404s to reduce noise.
ignoreregex = - 404 \d+ - \S+ \S+ \S+ "/(?:favicon\.ico|robots\.txt|sitemap\.xml|apple-touch-icon[^"]*|\.well-known/[^"]*)" \[Client <HOST>\]

View File

@@ -1,12 +1,19 @@
[Definition]
# ── NPM access log format ─────────────────────────────────────────────────────
# ── NPM access log format (current) ──────────────────────────────────────────
# [DD/Mon/YYYY:HH:MM:SS +0000] - STATUS STATUS - METHOD SCHEME HOST "PATH"
# [Client REAL_IP] [Length N] [Gzip N] [Sent-to IP] "UA" "REFERER"
#
# fail2ban strips the timestamp before applying failregex, leaving:
# " - STATUS STATUS - METHOD SCHEME HOST "PATH" [Client IP] ..."
#
# Bans IPs probing for well-known vulnerable paths.
# Default jail: 3 hits in 30 minutes → 48h ban (very aggressive, intentionally).
#
# PROXY_IP - - [date] "METHOD PATH HTTP/VER" STATUS BYTES "REFERER" "UA" [Client REAL_IP]
# Test against your logs:
# fail2ban-regex /nginx-logs/proxy-host-1_access.log /etc/fail2ban/filter.d/npm-probe.conf
# ─────────────────────────────────────────────────────────────────────────────
failregex = ^\S+ - - \[[^\]]+\] "[A-Z]+ /(?:\.env[^"]*|\.git[^"]*|wp-login\.php[^"]*|wp-admin[^"]*|xmlrpc\.php[^"]*|phpmyadmin[^"]*|pma/[^"]*|adminer[^"]*|admin\.php[^"]*|config\.php[^"]*|setup\.php[^"]*|install\.php[^"]*|actuator[^"]*|console[^"]*|manager/html[^"]*|invoker/[^"]*|solr/[^"]*|geoserver/[^"]*|boaform/[^"]*|HNAP1[^"]*|cgi-bin/[^"]*|shell\.php[^"]*|cmd\.php[^"]*|eval-stdin\.php[^"]*)[^"]*" \d{3} \d+ "[^"]*" "[^"]*" \[Client <HOST>\]
failregex = - \d+ \d+ - \S+ \S+ \S+ "/(?:\.env[^"]*|\.git[^"]*|wp-login\.php[^"]*|wp-admin[^"]*|xmlrpc\.php[^"]*|phpmyadmin[^"]*|pma/[^"]*|adminer[^"]*|admin\.php[^"]*|config\.php[^"]*|setup\.php[^"]*|install\.php[^"]*|actuator[^"]*|console[^"]*|manager/html[^"]*|invoker/[^"]*|solr/[^"]*|geoserver/[^"]*|boaform/[^"]*|HNAP1[^"]*|cgi-bin/[^"]*|shell\.php[^"]*|cmd\.php[^"]*|eval-stdin\.php[^"]*)[^"]*" \[Client <HOST>\]
ignoreregex =