ArliT1-F · ArliT1-F · Oct 27, 2025 · Oct 27, 2025 · Oct 27, 2025 · Oct 27, 2025
diff --git a/.github/workflows/websecscan.yml b/.github/workflows/websecscan.yml
@@ -0,0 +1,71 @@
+name: WebSecScan
+
+on:
+  schedule:
+    - cron: "0 3 * * *" # daily at 03:00 UTC
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+concurrency:
+  group: websecscan
+  cancel-in-progress: true
+
+jobs:
+  scan:
+    runs-on: ubuntu-latest
+    env:
+      VIRUSTOTAL_API_KEY: ${{ secrets.VIRUSTOTAL_API_KEY }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install WebSecScan
+        run: |
+          python -m pip install --upgrade pip
+          pip install .
+
+      - name: Run scans
+        run: |
+          mkdir -p reports
+          TS=$(date -u +%Y%m%d_%H%M%S)
+          if [ -f targets.txt ]; then
+            while IFS= read -r url; do
+              [ -z "$url" ] && continue
+              websecscan "$url" --output html --fast || true
+              dom=$(echo "$url" | sed 's|https\?://||; s|/||g')
+              if [ -f "reports/scan_${dom}.html" ]; then
+                mv "reports/scan_${dom}.html" "reports/${TS}_${dom}.html"
+              fi
+            done < targets.txt
+          else
+            echo "No targets.txt found; skipping scans."
+          fi
+          # Disable Jekyll on GitHub Pages
+          touch reports/.nojekyll
+
+          # Generate a simple index.html listing all report files
+          echo "<!doctype html><html><head><meta charset=\"utf-8\"><title>WebSecScan Reports</title><meta name=\"viewport\" content=\"width=device-width, initial-scale=1\"><style>body{font-family:system-ui,-apple-system,Segoe UI,Roboto,Ubuntu,\"Helvetica Neue\",sans-serif;max-width:900px;margin:40px auto;padding:0 16px}h1{margin:0 0 8px}small{color:#666}ul{line-height:1.8}code{background:#f4f4f4;padding:2px 6px;border-radius:4px}</style></head><body><h1>WebSecScan Reports</h1><small>Generated by GitHub Actions</small><hr><ul>" > reports/index.html
+          for f in $(ls -1t reports/*.html 2>/dev/null | sed 's|reports/||' | grep -v '^index.html$'); do
+            echo "<li><a href=\"$f\">$f</a></li>" >> reports/index.html
+          done
+          echo "</ul><p>To run a new scan, go to <a href=\"https://github.com/${GITHUB_REPOSITORY}/actions\">Actions</a> and trigger the <strong>WebSecScan</strong> workflow.</p></body></html>" >> reports/index.html
+
+      - name: Upload artifact (reports)
+        uses: actions/upload-artifact@v4
+        with:
+          name: reports-${{ github.run_number }}
+          path: reports/
+
+      - name: Publish to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_branch: gh-pages
+          publish_dir: reports
+          keep_files: true
diff --git a/MANIFEST.in b/MANIFEST.in
@@ -0,0 +1 @@
+recursive-include scanner/templates *
diff --git a/README.md b/README.md
@@ -105,6 +105,114 @@ python3 websecscan.py https://example.com --output md --active
 
 ---
 
+## 🚀 Run on GitHub (scheduled, auto-published reports)
+
+Follow these steps to host the project on GitHub and keep it running on a schedule via GitHub Actions. Reports will be committed to a `gh-pages` branch and published with GitHub Pages.
+
+### 1) Push this project to your GitHub repo
+- Create a new repository on GitHub (public or private)
+- From your local machine or CI environment:
+```bash
+git init
+git add .
+git commit -m "feat: initial import of WebSecScan"
+git branch -M main
+git remote add origin git@github.com:<your-username>/<your-repo>.git
+git push -u origin main
+```
+
+### 2) Add your VirusTotal API key as a secret
+- GitHub → Your repository → Settings → Secrets and variables → Actions → New repository secret
+- Name: `VIRUSTOTAL_API_KEY`
+- Value: your actual API key
+
+### 3) Add a `targets.txt` file (domains you own)
+- Create a file named `targets.txt` in the repo root containing one authorized URL per line, for example:
+```text
+https://example.com
+https://sub.example.com
+```
+
+### 4) Add the GitHub Actions workflow
+- Create the file `.github/workflows/websecscan.yml` with the following content:
+```yaml
+name: WebSecScan
+
+on:
+  schedule:
+    - cron: "0 3 * * *"   # daily at 03:00 UTC
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+concurrency:
+  group: websecscan
+  cancel-in-progress: true
+
+jobs:
+  scan:
+    runs-on: ubuntu-latest
+    env:
+      VIRUSTOTAL_API_KEY: ${{ secrets.VIRUSTOTAL_API_KEY }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install WebSecScan
+        run: |
+          python -m pip install --upgrade pip
+          pip install .
+
+      - name: Run scans
+        run: |
+          mkdir -p reports
+          TS=$(date -u +%Y%m%d_%H%M%S)
+          while IFS= read -r url; do
+            [ -z "$url" ] && continue
+            websecscan "$url" --output html --fast || true
+            dom=$(echo "$url" | sed 's|https\?://||; s|/||g')
+            if [ -f "reports/scan_${dom}.html" ]; then
+              mv "reports/scan_${dom}.html" "reports/${TS}_${dom}.html"
+            fi
+          done < targets.txt
+
+      - name: Upload artifact (reports)
+        uses: actions/upload-artifact@v4
+        with:
+          name: reports-${{ github.run_number }}
+          path: reports/
+
+      - name: Publish to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_branch: gh-pages
+          publish_dir: reports
+          keep_files: true
+```
+
+### 5) Enable GitHub Pages
+- Repo → Settings → Pages → Build and deployment
+- Source: `Deploy from a branch`
+- Branch: `gh-pages`, Folder: `/ (root)`
+- Save. Your reports will be available at `https://<your-username>.github.io/<your-repo>/`
+
+### 6) Run it now
+- Go to Actions → `WebSecScan` → Run workflow
+- After it finishes, view the Pages site or download the artifact
+
+### Notes and tips
+- Only include domains you own or are authorized to scan in `targets.txt`.
+- Remove `--fast` in the workflow to enable all checks (slower, more API use).
+- To keep history, the workflow timestamps report filenames; adjust as needed.
+- If you need private reports, skip GitHub Pages and rely on build artifacts only.
+- For heavy scans or tighter control, consider a VPS + `cron`/`systemd` instead of Actions.
+
 ## 🤝 Contributing
 Pull requests, feature suggestions, and plugins are welcome!
 Feel free to fork the project and submit your ideas, as I will be checking the project from time to time.
@@ -118,4 +226,4 @@ Built for security researchers, red teamers, and educators.
 ## ⚠️ Disclaimer
 Use responsibly.
 This tool is intended for **authorized testing only**.
-Do not scan websites without permission.
+Do not scan websites without permission.
diff --git a/reports/scan_example.com.md b/reports/scan_example.com.md
@@ -0,0 +1,76 @@
+# 🛡️ WebSecScan Report
+
+**Target:** https://example.com  
+**Scan Time:** 2025-10-27 18:28:40.472899
+
+---
+
+## 🔐 SSL Certificate
+
+- **issuer:** ((('countryName', 'US'),), (('organizationName', 'DigiCert Inc'),), (('commonName', 'DigiCert Global G3 TLS ECC SHA384 2020 CA1'),))
+
+- **subject:** ((('countryName', 'US'),), (('stateOrProvinceName', 'California'),), (('localityName', 'Los Angeles'),), (('organizationName', 'Internet Corporation for Assigned Names and Numbers'),), (('commonName', '*.example.com'),))
+
+- **valid_from:** Jan 15 00:00:00 2025 GMT
+
+- **valid_until:** Jan 15 23:59:59 2026 GMT
+
+
+---
+
+## 🧱 WAF Detection
+**WAF:** None detected
+
+---
+
+## 📑 Security Headers
+
+- **Content-Security-Policy:** Missing
+
+- **X-Content-Type-Options:** Missing
+
+- **Strict-Transport-Security:** Missing
+
+- **X-Frame-Options:** Missing
+
+
+---
+
+## 🧬 Tech Stack
+
+- None detected
+
+
+---
+
+## 📌 CVE Matches
+
+- None
+
+
+---
+
+## 📁 Sensitive Paths Found
+
+- None
+
+
+---
+
+## 📊 Risk Score
+**Score:** 25/100  
+
+- ⚠️ Missing headers: Content-Security-Policy, X-Content-Type-Options, Strict-Transport-Security, X-Frame-Options
+
+- ⚠️ No WAF detected
+
+
+---
+
+## 🔗 Links Analyzed
+
+### https://iana.org/domains/example
+
+- **IP:** 192.0.43.8
+- **WHOIS:** 
+- **Heuristics:**
diff --git a/requirements.txt b/requirements.txt
@@ -8,4 +8,5 @@ python-whois>=0.8.0
 Jinja2>=3.1.2
 aiodns>=3.0.0
 scikit-learn>1.3.0
-joblib>=1.3.2
+joblib>=1.3.2
+scikit-learn
diff --git a/scanner/__pycache__/__init__.cpython-313.pyc b/scanner/__pycache__/__init__.cpython-313.pyc
diff --git a/scanner/__pycache__/active_tester.cpython-313.pyc b/scanner/__pycache__/active_tester.cpython-313.pyc
diff --git a/scanner/__pycache__/anti_bot.cpython-313.pyc b/scanner/__pycache__/anti_bot.cpython-313.pyc
diff --git a/scanner/__pycache__/async_tools.cpython-313.pyc b/scanner/__pycache__/async_tools.cpython-313.pyc
diff --git a/scanner/__pycache__/auth_scanner.cpython-313.pyc b/scanner/__pycache__/auth_scanner.cpython-313.pyc
diff --git a/scanner/__pycache__/core.cpython-313.pyc b/scanner/__pycache__/core.cpython-313.pyc
diff --git a/scanner/__pycache__/dir_brute.cpython-313.pyc b/scanner/__pycache__/dir_brute.cpython-313.pyc
diff --git a/scanner/__pycache__/extract.cpython-313.pyc b/scanner/__pycache__/extract.cpython-313.pyc
diff --git a/scanner/__pycache__/headers.cpython-313.pyc b/scanner/__pycache__/headers.cpython-313.pyc
diff --git a/scanner/__pycache__/heuristics.cpython-313.pyc b/scanner/__pycache__/heuristics.cpython-313.pyc
diff --git a/scanner/__pycache__/ip_tools.cpython-313.pyc b/scanner/__pycache__/ip_tools.cpython-313.pyc
diff --git a/scanner/__pycache__/profiling.cpython-313.pyc b/scanner/__pycache__/profiling.cpython-313.pyc
diff --git a/scanner/__pycache__/recon.cpython-313.pyc b/scanner/__pycache__/recon.cpython-313.pyc
diff --git a/scanner/__pycache__/report.cpython-313.pyc b/scanner/__pycache__/report.cpython-313.pyc
diff --git a/scanner/__pycache__/smart_detect.cpython-313.pyc b/scanner/__pycache__/smart_detect.cpython-313.pyc
diff --git a/scanner/__pycache__/spider.cpython-313.pyc b/scanner/__pycache__/spider.cpython-313.pyc
diff --git a/scanner/__pycache__/ssl_analyzer.cpython-313.pyc b/scanner/__pycache__/ssl_analyzer.cpython-313.pyc
diff --git a/scanner/__pycache__/stack_fingerprint.cpython-313.pyc b/scanner/__pycache__/stack_fingerprint.cpython-313.pyc
diff --git a/scanner/__pycache__/subdomains.cpython-313.pyc b/scanner/__pycache__/subdomains.cpython-313.pyc
diff --git a/scanner/__pycache__/virustotal.cpython-313.pyc b/scanner/__pycache__/virustotal.cpython-313.pyc
diff --git a/scanner/__pycache__/vuln_check.cpython-313.pyc b/scanner/__pycache__/vuln_check.cpython-313.pyc
diff --git a/scanner/async_tools.py b/scanner/async_tools.py
@@ -52,7 +52,7 @@ def load_plugins(plugin_folder="plugins"):
                 spec.loader.exec_module(mod)
                 if hasattr(mod, "run_plugin"):
                     plugins.append(mod)
-        return plugins
+    return plugins
 
 def run_plugins(plugins, url, html, headers):
     results = []

diff --git a/scanner/core.py b/scanner/core.py
@@ -140,9 +140,9 @@ def scan_website(url, fast_mode=False, use_plugins=False, output_format="json",
                 soup = BeautifulSoup(resp.text, 'html.parser')
                 for script in soup.find_all('script'):
                     if script.string:
-                        js_snippets.appeend(script.string)
+                        js_snippets.append(script.string)
                 report["suspicious_analysis"] = is_url_suspicious(link, js_snippets)
-            except:
+            except Exception:
                 report["suspicious_analysis"] = {"error": "Failed to analyze scripts"}
 
 
@@ -157,10 +157,12 @@ def scan_website(url, fast_mode=False, use_plugins=False, output_format="json",
             report["ip"] = ip
             report["host_profile"] = get_host_profile(ip)
 
-        except:
+        except Exception:
             report["ip"] = None
             report["host_profile"] = {"error": "Could not resolve IP"}
-            scan_summary["reports"].append(report)
+
+        # Always record the report for this link
+        scan_summary["reports"].append(report)
 
     # Final risk score
     scan_summary["risk"] = calculate_risk_score(scan_summary)

diff --git a/scanner/extract.py b/scanner/extract.py
@@ -16,5 +16,5 @@ def extract_links(url):
 def detect_ip_grabber(url):
     import re
     patterns = [r'\d{10,}', r'[a-zA-Z]{20,}', r'[0-9a-f]{32}']
-    domains = ["grabify.link", "iplogger.org", "ipgrabber.io", "grabify.link"]
+    domains = ["grabify.link", "iplogger.org", "ipgrabber.io"]
     return any(re.search(p, url) for p in patterns) or any(d in url for d in domains)
diff --git a/scanner/headers.py b/scanner/headers.py
@@ -8,5 +8,5 @@ def analyze_headers(headers):
     return {h: headers.get(h, "Missing") for h in important}
 
 def detect_waf(headers):
-    waf_keys = ["Server", "X-CDN", "CF-RAY", "X-Sucuro-ID", "X-Akamai"]
+    waf_keys = ["Server", "X-CDN", "CF-RAY", "X-Sucuri-ID", "X-Akamai"]
     return {k: headers[k] for k in waf_keys if k in headers}
diff --git a/scanner/profiling.py b/scanner/profiling.py
@@ -99,7 +99,7 @@ def calculate_risk_score(scan_summary):
         if missing:
             penalties.append(f"Missing headers: {', '.join(missing)}")
 
-    if scan_summary.get("waf") in ["None", "", None]:
+    if not scan_summary.get("waf"):
         score += 5
         penalties.append("No WAF detected")
 
@@ -120,5 +120,4 @@ def calculate_risk_score(scan_summary):
 
 
     risk_score = min(score, 100)
-    return {"risk_score": risk_score, "penalties": penalties}
-
+    return {"risk_score": risk_score, "penalties": penalties}