build: Update DB [Mon Nov 11 00:52:09 UTC 2024]

.README.tmpl

@@ -0,0 +1,40 @@
+# teler Resource Collections
+
+![Kitabisa SecLab](https://img.shields.io/badge/kitabisa-security%20project-blue)
+
+This collection serves as the primary repository of external resources/datasets utilized by teler to identify potential threats. It is updated on a daily basis and undergoes automatic commit-and-push processes.
+
+## Statistics
+
+{{stats}}
+
+> [!NOTE]
+> Last updated at **{{updated_date}}**.
+
+## Contributions
+
+<a rel="license" href="http://creativecommons.org/licenses/by/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by/4.0/88x31.png" /></a>
+
+We express deep gratitude to the projects that have integrated their datasets. We explicitly state that we do **NOT** assert ownership or authorship of any of these resources. This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</a>.
+
+If you have any suggestions for additional resources that can aid in the development and advancement of the [teler](https://github.com/kitabisa/teler) or [teler-waf](https://github.com/kitabisa/teler-waf) project, we'd love to hear about them. :heart:
+
+- **Common Web Attack**
+
+  This is taken from the [PHPIDS](https://github.com/PHPIDS/PHPIDS) project; please see their [README](https://github.com/PHPIDS/PHPIDS#credits) for names of those who have contributed.
+
+- **CVEs**
+
+  The curated list of CVEs is derived from [Nuclei templates](https://github.com/projectdiscovery/nuclei-templates) provided by Project Discovery team, as well as contributions from the community.
+
+- **Bad IP Address** & **Bad Referrer**
+
+  Both collections belong to [Nginx Ultimate Bad Bot Blocker](https://github.com/mitchellkrogza/nginx-ultimate-bad-bot-blocker) project. Bad IP Addresses collection also includes a list of [ipsum](https://github.com/stamparm/ipsum) (level: **3+**).
+
+- **Bad Crawler**
+
+  This is taken from the [Crawler Detect](https://github.com/JayBizzle/Crawler-Detect) project, and you can find the names of contributors in the [Crawlers.txt](https://github.com/JayBizzle/Crawler-Detect/blob/master/raw/Crawlers.txt) file.
+
+- **Directory Bruteforce**
+
+  This collection is obtained from the [fuzz.txt](https://github.com/Bo0oM/fuzz.txt).

.github/dependabot.yaml

@@ -0,0 +1,8 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    labels:
+      - "package-ecosystem"

.github/scripts/convert-cves.py

@@ -0,0 +1,50 @@
+import json
+import os
+import yaml
+
+def get_parent_directory(path, levels=1):
+    levels = levels + 1 if os.path.isfile(path) else 0
+    for _ in range(levels):
+        path = os.path.dirname(path)
+    return path
+
+def convert_yaml_to_json(input_file):
+    with open(input_file, 'r') as f:
+        yaml_data = yaml.safe_load(f)
+
+    try:
+        json_data = {
+            "id": yaml_data['id'],
+            "info": {
+                "name": yaml_data['info']['name'],
+                "severity": yaml_data['info']['severity']
+            },
+            "requests": yaml_data['http']
+        }
+    except KeyError:
+        return False
+
+    return json_data
+
+def convert_cves(directory_path):
+    json_output = {"templates": []}
+    for root, _, files in os.walk(directory_path):
+        for file_name in files:
+            if file_name.endswith(".yaml"):
+                input_file = os.path.join(root, file_name)
+                json_data = convert_yaml_to_json(input_file)
+                if not json_data:
+                    continue
+                json_output["templates"].append(json_data)
+
+    return json_output
+
+if __name__ == "__main__":
+    input_dir = "/tmp/nuclei-templates-main/http/cves/"
+    workspace_dir = get_parent_directory(os.path.abspath(__file__), levels=2)
+    output_file = os.path.join(workspace_dir, "db", "cves.json")
+
+    converted_data = convert_cves(input_dir)
+
+    with open(output_file, 'w') as f:
+        json.dump(converted_data, f, separators=(',', ':'))

.github/scripts/generate-readme.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+
+function count() {
+	local path="db/${1}"
+
+	if [[ ! "${1}" =~ \.json$ ]]; then
+		wc -l "${path}" | awk '{print $1}'
+		return 0
+	fi
+
+	local prop
+	case "${1}" in
+		common-web-attacks* )
+			prop="filters"
+			;;
+		cves* )
+			prop="templates"
+			;;
+	esac
+	jq -r ".${prop} | length" "${path}"
+}
+
+CWA_count=$(count "common-web-attacks.json")
+CVEs_count=$(count "cves.json")
+BadIP_count=$(count "bad-ip-addresses.txt")
+BadRef_count=$(count "bad-referrers.txt")
+BadCrawl_count=$(count "bad-crawlers.txt")
+DirBrute_count=$(count "directory-bruteforces.txt")
+total_count=$((CWA_count + CVEs_count + BadIP_count + BadRef_count + BadCrawl_count + DirBrute_count))
+
+STATS_TABLE=${STATS_TABLE_TMPL}
+STATS_TABLE=$(echo "${STATS_TABLE}" | sed "s/{{CWA_count}}/${CWA_count}/")
+STATS_TABLE=$(echo "${STATS_TABLE}" | sed "s/{{CVEs_count}}/${CVEs_count}/")
+STATS_TABLE=$(echo "${STATS_TABLE}" | sed "s/{{BadIP_count}}/${BadIP_count}/")
+STATS_TABLE=$(echo "${STATS_TABLE}" | sed "s/{{BadRef_count}}/${BadRef_count}/")
+STATS_TABLE=$(echo "${STATS_TABLE}" | sed "s/{{BadCrawl_count}}/${BadCrawl_count}/")
+STATS_TABLE=$(echo "${STATS_TABLE}" | sed "s/{{DirBrute_count}}/${DirBrute_count}/")
+STATS_TABLE=$(echo "${STATS_TABLE}" | sed "s/{{total_count}}/${total_count}/")
+STATS_TABLE=$(echo "${STATS_TABLE}" | sed ':a;N;$!ba;s/\n/\\n/g')
+
+README_TMPL=$(cat .README.tmpl)
+README_TMPL=$(echo "${README_TMPL}" | sed "s/{{stats}}/${STATS_TABLE}/") # it doesn't work
+README_TMPL=$(echo "${README_TMPL}" | sed "s/{{updated_date}}/$(date)/")
+
+echo "${README_TMPL}"

.github/workflows/deploy-teler-waf-demo.yaml

@@ -0,0 +1,17 @@
+name: Deploy waf.teler.app
+
+on:
+  workflow_run:
+    workflows: ["Update resources database"]
+    types:
+      - completed
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    if: ${{ github.event.workflow_run.conclusion == 'success' }}
+    steps:
+      - name: Call Deploy Hook
+        env:
+          HOOK_URL: ${{ secrets.TELER_WAF_DEMO_DEPLOY_HOOK_URL }}
+        run: curl "${HOOK_URL}"

.github/workflows/update-db.yaml

@@ -0,0 +1,69 @@
+name: "Update resources database"
+
+on:
+  schedule:
+    - cron: "0 0 * * *"
+  workflow_dispatch:
+
+jobs:
+  update:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out code
+        uses: actions/checkout@master
+
+      - name: Configure Git
+        env:
+          USER: "ghost"
+          HOST: "users.noreply.github.com"
+        run: |
+          git config --local user.email "${USER}@${HOST}"
+          git config --local user.name "${USER}"
+
+      - name: Filtering branch (rm DB history)
+        env:
+          FILTER_BRANCH_SQUELCH_WARNING: "1"
+        run: git filter-branch --index-filter "git rm --cached --ignore-unmatch -r db/" $GITHUB_REF
+
+      - name: Install dependencies
+        run: sudo apt install jq zstd tar wget -y
+
+      - name: Downloading latest nuclei-templates
+        run: wget -q https://github.com/projectdiscovery/nuclei-templates/archive/refs/heads/main.zip && unzip main.zip
+        working-directory: "/tmp"
+
+      - name: Downloading other resources
+        run: |
+          mkdir -p db
+          wget -q "https://raw.githubusercontent.com/Bo0oM/fuzz.txt/master/fuzz.txt" -O "db/directory-bruteforces.txt" &
+          wget -q "https://raw.githubusercontent.com/dwisiswant0/cwa-filter-rules/master/dist/filters.json" -O "db/common-web-attacks.json" &
+          wget -q "https://raw.githubusercontent.com/JayBizzle/Crawler-Detect/master/raw/Crawlers.txt" -O "db/bad-crawlers.txt" &
+          wget -q "https://raw.githubusercontent.com/mitchellkrogza/nginx-ultimate-bad-bot-blocker/master/_generator_lists/bad-referrers.list" -O "db/bad-referrers.txt" &
+          wget -qP /tmp "https://raw.githubusercontent.com/mitchellkrogza/nginx-ultimate-bad-bot-blocker/master/_generator_lists/bad-ip-addresses.list" &
+          wget -qP /tmp "https://raw.githubusercontent.com/stamparm/ipsum/master/levels/3.txt" &
+          wait
+          sort -u /tmp/bad-ip-addresses.list /tmp/3.txt > "db/bad-ip-addresses.txt"
+
+      - name: Convert CVEs resources
+        run: python .github/scripts/convert-cves.py
+
+      - name: Build DB
+        env:
+          DB: "db.tar.zst"
+        working-directory: "db/"
+        run: rm -f *.zst MD5SUMS; tar -cf - * | zstd -o "${DB}"; md5sum * > MD5SUMS
+
+      - name: Generate README
+        env:
+          STATS_TABLE_TMPL: ${{ vars.STATS_TABLE_TMPL }}
+        run: bash .github/scripts/generate-readme.sh | tee README.md
+
+      - name: Push resources
+        run: |
+          COMMIT_MSG="build: "
+          [[ "${{ github.event_name }}" == "workflow_dispatch" ]] && COMMIT_MSG+="[force] "
+          COMMIT_MSG+="Update DB [$(date)]"
+
+          git add .
+          git commit -m "${COMMIT_MSG}"
+          git push origin master -f

.gitignore

@@ -0,0 +1,4 @@
+get-resources.sh
+auto-commit.sh
+cves.go
+go.*