Merge branch 'Zeecka:main' into main

Dockerfile

@@ -26,17 +26,20 @@ RUN wget https://github.com/syvaidya/openstego/releases/download/openstego-0.8.6
     dpkg -i /tmp/openstego.deb && \
     rm /tmp/openstego.deb
 
-# Clean up apt cache and remove useless packages
+# Copy application
-RUN apt-get remove -y wget && \
-    apt-get clean && \
-    rm -rf /var/lib/apt/lists/*
-
 COPY aperisolve/ /aperisolve/
 
 RUN mkdir -p /data
 
+# Install Python dependencies
 RUN pip install --no-cache-dir -r /aperisolve/requirements.txt
 
 ENV PYTHONUNBUFFERED=1
 
+# Auto clean after build
+RUN apt-get remove -y wget && \
+    apt-get autoremove -y && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
 CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:5000", "--access-logfile", "-", "--error-logfile", "-", "--log-level", "info", "--capture-output", "aperisolve.wsgi:application"]

aperisolve/analyzers/binwalk.py

@@ -3,6 +3,7 @@
 import shutil
 import subprocess
 from pathlib import Path
+from typing import Any
 
 from .utils import MAX_PENDING_TIME, update_data
 
@@ -17,7 +18,7 @@ def analyze_binwalk(input_img: Path, output_dir: Path) -> None:
         stderr = ""
         # Run binwalk
         data = subprocess.run(
-            ["binwalk", "-e", "../" + str(image_name), "--run-as=root"],
+            ["binwalk", "--matryoshka", "-e", "../" + str(image_name), "--run-as=root"],
             cwd=output_dir,
             capture_output=True,
             text=True,
@@ -47,16 +48,17 @@ def analyze_binwalk(input_img: Path, output_dir: Path) -> None:
         # Only report error if stderr exists AND extraction failed.
         # If zip_exist is True, binwalk worked (despite warnings), so we proceed.
         if len(stderr) > 0 and not zip_exist:
-            err = {
+            err: dict[str, dict[str, Any]] = {
                 "binwalk": {
                     "status": "error",
+                    "output": data.stdout.split("\n") if data else [],
                     "error": stderr,
                 }
             }
             update_data(output_dir, err)
             return None
 
-        output_data = {
+        output_data: dict[str, dict[str, Any]] = {
             "binwalk": {
                 "status": "ok",
                 "output": data.stdout.split("\n") if data else [],

aperisolve/app.py

@@ -6,6 +6,7 @@ import os
 import time
 from datetime import datetime, timezone
 from pathlib import Path
+from shutil import rmtree
 from typing import Any, Optional
 
 from flask import Flask, Response, abort, jsonify, render_template, request, send_file
@@ -112,34 +113,33 @@ def upload_image() -> tuple[Response, int]:
     submission_hash = hashlib.md5(submission_data).hexdigest()
     submission_path = RESULT_FOLDER / img_hash / submission_hash
 
-    # Check if hash is present on the DB
+    # If submission already exists, return submission hash
-    submission: Submission = Submission.query.filter_by(
+    if submission_path.exists():
-        hash=submission_hash
+        submission: Submission = Submission.query.filter_by(
-    ).first()
+            hash=submission_hash
+        ).first()
 
-    # Only return if BOTH the file exists AND the DB entry exists
+        if submission is not None:  # File exist but not in DB (should not happen),
-    if submission_path.exists() and submission is not None:
+            rmtree(submission_path)  # Removing file and continue processing as new
-        return jsonify({"submission_hash": submission.hash}), 200
+            db.session.delete(submission)  # pylint: disable=no-member
+            db.session.commit()  # pylint: disable=no-member
+        else:
+            return jsonify({"submission_hash": submission.hash}), 200
 
-
+    # If image is new, create a new Image entry
-    # Self-Healing Logic
     new_img_path = RESULT_FOLDER / img_hash / image_name
+    sub_img = Image.query.filter_by(hash=img_hash).first()  # type: ignore
 
-    # Try to find image in DB by hash
+    if new_img_path.parent.exists() and sub_img is None:
-    sub_img = Image.query.filter_by(
+        # Inconsistent state: image file exists but no DB entry
-        hash=img_hash
+        rmtree(new_img_path.parent)  # Remove the existing files and continue
-    ).first()
 
-    # If DB entry is missing (even if file exists on disk), create it!
+    if not new_img_path.parent.exists():
-    if sub_img is None:
+        new_img_path.parent.mkdir(parents=True, exist_ok=True)
-        if not new_img_path.parent.exists() or not new_img_path.exists():
+        with open(new_img_path, "wb") as f:  # Write file to disk
-            new_img_path.parent.mkdir(parents=True, exist_ok=True)
+            f.write(image_data)
-            with open(new_img_path, "wb") as f:
-                f.write(image_data)
 
-
+        new_img = Image(
-        # Recreate the missing Database Entry
-        sub_img = Image(
             file=str(new_img_path),
             hash=img_hash,
             size=len(image_data),
@@ -147,39 +147,33 @@ def upload_image() -> tuple[Response, int]:
             first_submission_date=datetime.now(timezone.utc),
             last_submission_date=datetime.now(timezone.utc),
         )
-        db.session.add(sub_img)
+        db.session.add(new_img)  # pylint: disable=no-member
-        db.session.commit()
+        db.session.commit()  # pylint: disable=no-member
 
-    # Increment upload count for the image
+    sub_img = Image.query.filter_by(hash=img_hash).first()  # type: ignore
     sub_img.upload_count += 1
-    db.session.commit()
+    db.session.commit()  # pylint: disable=no-member
 
     # Create new Submission entry
     submission_path.mkdir(parents=True, exist_ok=True)
+    submission = Submission(
+        filename=image.filename,
+        password=password,
+        deep_analysis=deep_analysis,
+        hash=submission_hash,
+        status="pending",
+        date=time.time(),
+        image_hash=sub_img.hash,  # type: ignore
+    )
+    db.session.add(submission)  # pylint: disable=no-member
 
-    # Only create a new submission if it does not already exist
+    db.session.commit()  # pylint: disable=no-member
-    # New submission for new image
-    if not submission:
-        submission = Submission(
-            filename=image.filename,
-            password=password,
-            deep_analysis=deep_analysis,
-            hash=submission_hash,
-            status="pending",
-            date=time.time(),
-            image_hash=sub_img.hash,
-        )
-        db.session.add(submission)
-        db.session.commit()
-
     # Start the analysis jobs
     queue.enqueue("aperisolve.workers.analyze_image", submission.hash, job_timeout=300)
 
-    # Return submission identifier
     return jsonify({"submission_hash": submission.hash}), 200
 
 
-
 @app.route("/status/<hash_val>", methods=["GET"])
 def get_status(hash_val: str) -> Response:
     """Get the processing status of a submission."""

aperisolve/static/js/aperisolve.js

@@ -252,6 +252,38 @@ function parseResult(result) {
 
     analyzer.innerHTML += `<h2>${capitalize(tool.replace("_"," "))}</h2>`;
 
+    // Parse text output
+    if (typeof result[tool]["output"] === "string") {
+      analyzer.innerHTML += `<pre>${escapeHtml(
+        result[tool]["output"]
+      )}</pre>`;
+    } else if (Array.isArray(result[tool]["output"])) {
+      if (result[tool]["output"].length > 0) {
+        var texarea_content = `<div class="textarea-container">`;
+        texarea_content += `<textarea class="form-control w-100 mb-2" rows="8" readonly>`;
+        for (const line of result[tool]["output"]) {
+          texarea_content += escapeHtml(`${line}\n`);
+        }
+        texarea_content += `</textarea>`;
+        texarea_content += `<i class="fas fa-copy copy-icon"></i>`;
+        texarea_content += `</div>`;
+        analyzer.innerHTML += texarea_content;
+      }
+    } else if (typeof result[tool]["output"] === "object") {
+      var table_content = `<div class="table-container">`;
+      table_content += `<table>`;
+      for (const key in result[tool]["output"]) {
+        table_content += `<tr><td>${escapeHtml(key)}</td>`;
+        table_content += `<td>${escapeHtml(
+          result[tool]["output"][key]
+        )}</td></tr>`;
+      }
+      table_content += `</table>`;
+      table_content += `</table>`;
+      analyzer.innerHTML += table_content;
+    }
+
+    // Parse images, downloads, ...
     if (result[tool]["status"] === "ok") {
       if ("images" in result[tool]) {
         // Parse image output
@@ -286,41 +318,6 @@ function parseResult(result) {
         }
       }
 
-      // Parse text output
-
-
-      if (typeof result[tool]["output"] === "string") {
-        analyzer.innerHTML += `<pre>${escapeHtml(
-          result[tool]["output"]
-        )}</pre>`;
-      } else if (Array.isArray(result[tool]["output"])) {
-        if (result[tool]["output"].length > 0) {
-          var texarea_content = `<div class="textarea-container">`;
-          texarea_content += `<textarea class="form-control w-100 mb-2" rows="8" readonly>`;
-          for (const line of result[tool]["output"]) {
-            texarea_content += escapeHtml(`${line}\n`);
-          }
-          texarea_content += `</textarea>`;
-          texarea_content += `<i class="fas fa-copy copy-icon"></i>`;
-          texarea_content += `</div>`;
-          analyzer.innerHTML += texarea_content;
-        }
-      } else if (typeof result[tool]["output"] === "object") {
-        var table_content = `<div class="table-container">`;
-        table_content += `<table>`;
-        for (const key in result[tool]["output"]) {
-          table_content += `<tr><td>${escapeHtml(key)}</td>`;
-          table_content += `<td>${escapeHtml(
-            result[tool]["output"][key]
-          )}</td></tr>`;
-        }
-        table_content += `</table>`;
-        table_content += `</table>`;
-        analyzer.innerHTML += table_content;
-      } else {
-        // analyzer.innerHTML += `<pre>${result[tool]["output"]}</pre>`;
-      }
-
       if ("download" in result[tool]) {
         // Parse download link
         analyzer.innerHTML += `<br/><a href="${escapeHtml(