adding back in rules

Readme.md

@@ -43,7 +43,6 @@ SneakyScope fetches a page in a sandbox, enriches with WHOIS/GeoIP, and runs a u
 * **Playwright** for headless page fetch/render
 * **BeautifulSoup4** for parsing
 * **Rules Engine**
-
   * YAML regex rules (`config/suspicious_rules.yaml`)
   * Function rules (`app/rules/function_rules.py`) registered on startup
 * **Artifacts**: persistent path mounted at `/data` (configurable)

app/__init__.py

@@ -12,6 +12,7 @@ from app.app_settings import AppSettings
 from app.blueprints.main import bp as main_bp  # ui blueprint
 from app.blueprints.api import api_bp as api_bp  # api blueprint
 from app.blueprints.roadmap import bp as roadmap_bp # roadmap
+from app.blueprints.changelog import bp as changelog_bp # changelog
 
   
 
@@ -63,6 +64,7 @@ def create_app() -> Flask:
 
     # roadmap file
     app.config["ROADMAP_FILE"] = str(Path(app.root_path) / "docs" / "roadmap.yaml")
+    app.config["CHANGELOG_FILE"] = str(Path(app.root_path) / "docs" / "changelog.yaml")
 
     # Configure storage directory (bind-mount is still handled by sandbox.sh)
     sandbox_storage_default = Path("/data")
@@ -73,6 +75,7 @@ def create_app() -> Flask:
     app.register_blueprint(main_bp)
     app.register_blueprint(api_bp)
     app.register_blueprint(roadmap_bp)
+    app.register_blueprint(changelog_bp)
 
     app_logger = get_app_logger()
 

app/blueprints/changelog.py

@@ -0,0 +1,71 @@
+# app/services/changelog_loader.py
+from __future__ import annotations
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, List, Optional, Dict
+import yaml
+
+from flask import Blueprint, current_app, render_template
+
+@dataclass
+class ChangeItem:
+    title: str
+    details: List[str]
+
+@dataclass
+class VersionLog:
+    version: str
+    features: List[ChangeItem]
+    refactors: List[ChangeItem]
+    fixes: List[ChangeItem]
+    notes: List[str]
+
+@dataclass
+class Changelog:
+    unreleased: Dict[str, List[ChangeItem]]
+    versions: List[VersionLog]
+
+def _coerce_items(items: Optional[List[Dict[str, Any]]]) -> List[ChangeItem]:
+    out: List[ChangeItem] = []
+    for it in items or []:
+        title = str(it.get("title", "")).strip()
+        details = [str(d) for d in (it.get("details") or [])]
+        out.append(ChangeItem(title=title, details=details))
+    return out
+
+def load_changelog(path: Path) -> Changelog:
+    """
+    Load changelog.yaml and coerce into dataclasses.
+    """
+    data = yaml.safe_load(path.read_text(encoding="utf-8"))
+
+    unreleased = {
+        "features": _coerce_items(data.get("unreleased", {}).get("features")),
+        "refactors": _coerce_items(data.get("unreleased", {}).get("refactors")),
+        "fixes": _coerce_items(data.get("unreleased", {}).get("fixes")),
+    }
+
+    versions: List[VersionLog] = []
+    for v in data.get("versions", []):
+        versions.append(
+            VersionLog(
+                version=str(v.get("version")),
+                features=_coerce_items(v.get("features")),
+                refactors=_coerce_items(v.get("refactors")),
+                fixes=_coerce_items(v.get("fixes")),
+                notes=[str(n) for n in (v.get("notes") or [])],
+            )
+        )
+
+    return Changelog(unreleased=unreleased, versions=versions)
+
+
+bp = Blueprint("changelog", __name__)
+
+@bp.route("/changelog")
+def view_changelog():
+    # Configurable path with sensible default at project root
+    cfg_path = current_app.config.get("CHANGELOG_FILE")
+    path = Path(cfg_path) if cfg_path else (Path(current_app.root_path).parent / "changelog.yaml")
+    changelog = load_changelog(path)
+    return render_template("changelog.html", changelog=changelog)

app/docs/changelog.yaml

@@ -0,0 +1,80 @@
+# changelog.yaml
+unreleased:
+  features: []
+  refactors: []
+  fixes: []
+
+versions:
+  - version: "v0.2"
+    features:
+      - title: "UI Modernization"
+        details:
+          - "Migrated front-end to Tailwind CSS (compiled) with Flowbite JS components."
+          - "New navbar and layout system; better navigation and future expansion."
+          - "Docker-based CSS build for reproducible, lightweight builds."
+      - title: "Reusable CSS Components"
+        details:
+          - "Custom utilities: badge, badge-ok, badge-warn, badge-danger, chip, card, etc."
+          - "Reduces repetition and enforces consistent look."
+      - title: "Roadmap / Changelog (YAML-driven + in-app UI)"
+        details:
+          - "YAML-backed roadmap, in-app view at `/roadmap`."
+          - "Roadmap Filters: q, tag, min_priority, milestone; tag chips; Details modal that renders `details`."
+          - "YAML-backed Changelog, in-app view at `/changelog`."
+      - title: "Modal sizing & ergonomics"
+        details:
+          - "Wider modal at larger breakpoints; scrollable body for long content."
+      - title: "GeoIP Results Uplift"
+        details:
+          - "Cloudflare detection via GeoIP ASN; badge on results page."
+          - "Country/ASN notes shown beside collapsed IP next to GeoIP results."
+      - title: "Text Analysis Pipeline (Rules)"
+        details:
+          - "`analyse_text()` extracts visible text and evaluates `category: text` rules."
+          - "Captures matched phrases into deduped `content_snippet` (len capped via `settings.ui.snippet_preview_len`)."
+          - "Results exposed in JSON as `suspicious_text`; UI via `templates/partials/result_text.html`."
+    refactors:
+      - title: "Template Includes"
+        details:
+          - "Common UI (headers/footers/layout) extracted into Jinja includes."
+      - title: "Roadmap loader simplification"
+        details:
+          - "Removed cache; returns typed dataclasses and normalizes `details`."
+      - title: "Safer JSON in templates"
+        details:
+          - "Use `|tojson|forceescape` for embedding payloads in data attributes."
+      - title: "Rules Engine Regex handling"
+        details:
+          - "Honor per-rule regex flags; default IGNORECASE for `category: text` if no `i` flag."
+      - title: "Engine/Scanner logging"
+        details:
+          - "Dispatch-time visibility; gated by `settings.app.print_rule_dispatch`."
+      - title: "Code cleanup"
+        details:
+          - "Removed obsolete paths/utilities; removed duplicate `enrich_url` call."
+    fixes:
+      - title: "Table Rendering"
+        details:
+          - "Locked column widths; fixed snippet scaling to prevent reflow."
+      - title: "Rules Engine State"
+        details:
+          - "Fix pulling engine from app state; restores proper detections."
+      - title: "YAML parsing edge cases"
+        details:
+          - "Quote scalars containing `:`/`#`; use explicit `null` as needed."
+      - title: "/roadmap page stability"
+        details:
+          - "Return structured objects; fix `AttributeError: 'dict' object has no attribute 'roadmap'`."
+      - title: "Modal population"
+        details:
+          - "Pass `details` through route; DOM-ready + delegation populate reliably."
+      - title: "Text indicators not displayed"
+        details:
+          - "Add text analyzer; align result shape with `result_text` partial."
+
+  - version: "v0.1"
+    notes:
+      - "Initial Flask web UI for URL submission and analysis."
+      - "Domain & IP enrichment (WHOIS, GeoIP, ASN/ISP)."
+      - "First Suspicious Rules Engine for scripts/forms."
+      - "Basic Docker setup for sandboxed deployment."

app/docs/roadmap.yaml

@@ -2,18 +2,6 @@
 updated: "2025-08-22"
 
 roadmap:
-  - id: "p1-analysis-cloudflare"
-    priority: 1
-    title: "Cloudflare Detection"
-    goal: "Detect Cloudflare usage and badge it, with explanation of dual-use (security vs. abuse)."
-    tags: ["analysis"]
-    milestone: null
-    details:
-      - "Detection signals: DNS (CNAME to Cloudflare, AS13335), HTTP headers (cf-ray, cf-cache-status), IP ranges, and challenge pages."
-      - "UI: add badge + tooltip with a short explainer about legitimate protection vs. abuse evasion."
-      - "Edge cases: 'grey-clouded' DNS entries, partial proxy (only some records), and CDN in front of non-HTTP services."
-      - "Acceptance: correctly identifies Cloudflare on known test hosts and avoids false positives on non-CF CDNs."
-
   - id: "p1-analysis-total-score"
     priority: 1
     title: "Total Score"
@@ -26,15 +14,6 @@ roadmap:
       - "Explainability: always show a breakdown and contribution per component; include a 'Why?' link in the UI."
       - "Calibration: start with heuristic weights, then calibrate on a test set; store weights in settings.yaml."
 
-  - id: "p1-modal-close-fast"
-    priority: 1
-    title: "Analyze modal closes too fast"
-    goal: "have it wait until page reload"
-    tags: ["ui"]
-    milestone: null
-    details:
-      - "UX: user sees modal removed too quickly and thinks something broke"
-
   - id: "p2-ui-rules-lab"
     priority: 2
     title: "Rules Lab"

app/rules/factory.py

@@ -43,24 +43,24 @@ def build_rules_engine() -> RuleEngine:
     function=FunctionRuleAdapter(form_action_missing, category="form", adapter=adapter, rule_name="form_action_missing"),
     ))
 
-    # add(Rule(
-    # name="form_http_on_https_page",
-    # description="Form submits via HTTP from HTTPS page",
-    # category="form",
-    # rule_type="function",
-    # function=FunctionRuleAdapter(form_http_on_https_page, category="form", adapter=adapter, rule_name="form_http_on_https_page"),
-    # ))
+    add(Rule(
+    name="form_http_on_https_page",
+    description="Form submits via HTTP from HTTPS page",
+    category="form",
+    rule_type="function",
+    function=FunctionRuleAdapter(form_http_on_https_page, category="form", adapter=adapter, rule_name="form_http_on_https_page"),
+    ))
 
-    # add(Rule("form_http_on_https_page", "Form submits via HTTP from HTTPS page", "form", "function",
-    #          FunctionRuleAdapter(form_http_on_https_page, category="form", adapter=adapter, rule_name="form_http_on_https_page")))
-    # add(Rule("form_submits_to_different_host", "Form submits to a different host", "form", "function",
-    #          FunctionRuleAdapter(form_submits_to_different_host, category="form", adapter=adapter, rule_name="form_submits_to_different_host")))
-    # add(Rule("script_src_uses_data_or_blob", "Script src uses data:/blob: URL", "script", "function",
-    #          FunctionRuleAdapter(script_src_uses_data_or_blob, category="script", adapter=adapter, rule_name="script_src_uses_data_or_blob")))
-    # add(Rule("script_src_has_dangerous_extension", "External script with dangerous extension", "script", "function",
-    #          FunctionRuleAdapter(script_src_has_dangerous_extension, category="script", adapter=adapter, rule_name="script_src_has_dangerous_extension")))
-    # add(Rule("script_third_party_host", "Script is from a third-party host", "script", "function",
-    #          FunctionRuleAdapter(script_third_party_host, category="script", adapter=adapter, rule_name="script_third_party_host")))
+    add(Rule("form_http_on_https_page", "Form submits via HTTP from HTTPS page", "form", "function",
+             FunctionRuleAdapter(form_http_on_https_page, category="form", adapter=adapter, rule_name="form_http_on_https_page")))
+    add(Rule("form_submits_to_different_host", "Form submits to a different host", "form", "function",
+             FunctionRuleAdapter(form_submits_to_different_host, category="form", adapter=adapter, rule_name="form_submits_to_different_host")))
+    add(Rule("script_src_uses_data_or_blob", "Script src uses data:/blob: URL", "script", "function",
+             FunctionRuleAdapter(script_src_uses_data_or_blob, category="script", adapter=adapter, rule_name="script_src_uses_data_or_blob")))
+    add(Rule("script_src_has_dangerous_extension", "External script with dangerous extension", "script", "function",
+             FunctionRuleAdapter(script_src_has_dangerous_extension, category="script", adapter=adapter, rule_name="script_src_has_dangerous_extension")))
+    add(Rule("script_third_party_host", "Script is from a third-party host", "script", "function",
+             FunctionRuleAdapter(script_third_party_host, category="script", adapter=adapter, rule_name="script_third_party_host")))
 
     log.info("Registered %d total rules (YAML + function)", len(eng.rules))
     return eng

app/templates/base.html

@@ -35,6 +35,11 @@
               Roadmap
             </a>
           </li>
+          <li>
+            <a href="{{ url_for('changelog.view_changelog') }}">
+              Changelog
+            </a>
+          </li>
         </ul>
 
         {# Mobile toggle #}
@@ -62,6 +67,11 @@
               Roadmap
             </a>
           </li>
+          <li>
+            <a href="{{ url_for('changelog.view_changelog') }}">
+              Chnagelog
+            </a>
+          </li>
         </ul>
       </div>
     </div>

app/templates/changelog.html

@@ -0,0 +1,136 @@
+{# templates/changelog.html #}
+{% extends "base.html" %}
+{% block title %}Changelog{% endblock %}
+
+{% block content %}
+<div class="mx-auto max-w-6xl px-4 py-6">
+  <!-- Header -->
+  <div class="mb-6 flex flex-col gap-2 sm:flex-row sm:items-end sm:justify-between">
+    <div>
+      <h1 class="text-2xl font-semibold tracking-tight">SneakyScope Changelog</h1>
+      {% if updated %}
+        <p class="text-sm text-gray-400">Last updated: {{ updated }}</p>
+      {% endif %}
+    </div>
+  </div>
+
+  {# Unreleased #}
+  {% set ur = changelog.unreleased %}
+  {% if ur.features or ur.refactors or ur.fixes %}
+    <section class="mb-8 rounded-2xl border border-gray-700 bg-gray-900 p-5">
+      <div class="mb-3 flex items-center gap-3">
+        <h2 class="text-xl font-semibold">Unreleased</h2>
+        <span class="badge badge-warn">WIP</span>
+      </div>
+
+      <div class="grid gap-6 md:grid-cols-3">
+        {% for title, items, icon in [
+          ("✨ Features", ur.features, "✨"),
+          ("🛠️ Refactors", ur.refactors, "🛠️"),
+          ("🐛 Fixes", ur.fixes, "🐛"),
+        ] %}
+          <div class="rounded-xl border border-gray-800 bg-gray-950 p-4">
+            <h3 class="mb-2 text-sm font-semibold text-gray-200">{{ title }}</h3>
+            {% if items and items|length %}
+              <ul class="space-y-3">
+                {% for it in items %}
+                  <li class="rounded-lg border border-gray-800 bg-gray-900 p-3">
+                    <div class="mb-1 font-medium">{{ it.title }}</div>
+                    {% if it.details %}
+                      <ul class="ml-5 list-disc text-sm text-gray-300">
+                        {% for d in it.details %}
+                          <li>{{ d }}</li>
+                        {% endfor %}
+                      </ul>
+                    {% endif %}
+                  </li>
+                {% endfor %}
+              </ul>
+            {% else %}
+              <p class="text-sm text-gray-400">Nothing yet — add upcoming {{ title.split(' ')[1] | lower }} here.</p>
+            {% endif %}
+          </div>
+        {% endfor %}
+      </div>
+    </section>
+  {% endif %}
+
+  {# Versions Accordion #}
+  <section>
+    <div id="changelog-accordion" data-accordion="collapse" class="divide-y rounded-2xl border border-gray-700 bg-gray-900">
+      {% for v in changelog.versions %}
+        <h2 id="acc-head-{{ loop.index }}">
+          <button type="button"
+                  class="flex w-full items-center justify-between px-5 py-4 text-left hover:bg-gray-800"
+                  data-accordion-target="#acc-body-{{ loop.index }}"
+                  aria-expanded="{{ 'true' if loop.first else 'false' }}"
+                  aria-controls="acc-body-{{ loop.index }}">
+            <span class="flex items-center gap-3">
+              <span class="font-semibold">{{ v.version }}</span>
+              {% if v.notes and not (v.features or v.refactors or v.fixes) %}
+                <span class="badge badge-ok">Notes only</span>
+              {% endif %}
+            </span>
+            <svg class="h-5 w-5 text-gray-300" aria-hidden="true" fill="none" viewBox="0 0 10 6">
+              <path stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M9 5 5 1 1 5"/>
+            </svg>
+          </button>
+        </h2>
+
+        <div id="acc-body-{{ loop.index }}"
+             class="{{ '' if loop.first else 'hidden' }}"
+             aria-labelledby="acc-head-{{ loop.index }}">
+          <div class="space-y-8 px-5 pb-5 pt-1">
+
+            {% if v.notes and v.notes|length %}
+              <div>
+                <h3 class="mb-2 text-sm font-semibold text-gray-200">Notes</h3>
+                <ul class="ml-6 list-disc text-sm text-gray-300">
+                  {% for n in v.notes %}
+                    <li>{{ n }}</li>
+                  {% endfor %}
+                </ul>
+              </div>
+            {% endif %}
+
+            {% for section_title, items in [
+              ("✨ Features", v.features),
+              ("🛠️ Refactors", v.refactors),
+              ("🐛 Fixes", v.fixes),
+            ] %}
+              {% if items and items|length %}
+                <div>
+                  <h3 class="mb-2 text-sm font-semibold text-gray-200">{{ section_title }}</h3>
+                  <div class="grid grid-cols-1 gap-3 md:grid-cols-2">
+                    {% for it in items %}
+                      <article class="rounded-2xl border border-gray-800 bg-gray-950 p-4">
+                        <h4 class="mb-1 font-semibold leading-snug">{{ it.title }}</h4>
+                        {% if it.details %}
+                          <ul class="ml-5 list-disc text-sm text-gray-300">
+                            {% for d in it.details %}
+                              <li>{{ d }}</li>
+                            {% endfor %}
+                          </ul>
+                        {% endif %}
+                      </article>
+                    {% endfor %}
+                  </div>
+                </div>
+              {% endif %}
+            {% endfor %}
+
+          </div>
+        </div>
+      {% endfor %}
+    </div>
+  </section>
+</div>
+{% endblock %}
+
+{% block scripts %}
+{# If you’re not auto-initializing Flowbite elsewhere, ensure its JS is loaded globally. #}
+<script>
+/* Optional: if you ever render details as HTML snippets, ensure they are trusted or sanitized server-side. */
+/* No extra JS needed here if Flowbite handles [data-accordion]. */
+</script>
+{% endblock %}

app/templates/partials/result_enrichment.html

@@ -37,6 +37,9 @@
           {{ ip }} - 
           {% if info.country %} {{ info.country }} {% endif %} -
           {% if info.isp %} {{ info.isp }} {% endif %}
+          {% if info.cloudflare %} 
+          <span class="badge badge-warn">Cloudflare </span>
+          {% endif %}
           
         </summary>
         <div class="px-3 pb-3 overflow-x-auto">

app/utils/enrichment.py

@@ -336,6 +336,9 @@ def enrich_whois(hostname: str) -> dict:
 
 def enrich_geoip(hostname: str) -> dict:
     """Resolve hostname to IPs and fetch info from ip-api.com."""
+
+    CLOUDFLARE_ASN = "AS13335 Cloudflare"
+
     geo_info = {}
     ips = extract_ips_from_url(hostname)
     for ip in ips:
@@ -352,6 +355,12 @@ def enrich_geoip(hostname: str) -> dict:
             resp = requests.get(f"http://ip-api.com/json/{ip_str}?fields=24313855", timeout=5)
             if resp.status_code == 200:
                 geo_info[ip_str] = resp.json()
+                asname = geo_info[ip_str].get("as")
+
+                # if behind cloudflare
+                if CLOUDFLARE_ASN in asname:
+                    geo_info[ip_str].update({"cloudflare":True})
+                    
             else:
                 geo_info[ip_str] = {"error": f"HTTP {resp.status_code}"}
         except Exception as e:

docs/changelog.md

@@ -17,7 +17,7 @@ This project follows [Semantic Versioning](https://semver.org/).
 - _Nothing yet — add upcoming fixes here._
 
 ---
-
+## [v0.2]
 
 ### ✨ Features
 
@@ -37,6 +37,10 @@ This project follows [Semantic Versioning](https://semver.org/).
 * **Modal sizing & ergonomics**
   Increased modal width at larger breakpoints and made the body scrollable so long details don’t squish other content.
 
+* **GeoIP Results Uplift**
+  Added Cloudflare detection via Geoip ASN results and Cloudflare badge on results page
+  Added Country - ASN notes beside collapsed IP next to GeoIP results for quick viewing.
+
 * **Text Analysis Pipeline (Rules)**
   Implemented `analyse_text()` to extract visible page text and evaluate `category: text` rules.
   Captures matched phrases into a deduped `content_snippet` (length capped via `settings.ui.snippet_preview_len`).
@@ -88,7 +92,7 @@ This project follows [Semantic Versioning](https://semver.org/).
 
 ---
 
-## [v0.1] – Initial Work
+## [v0.1]
 
 - Implemented initial **Flask-based web UI** for URL submission and analysis.
 - Added **domain & IP enrichment** (WHOIS, GeoIP, ASN/ISP lookups).