Create entropy-beauty-scan.yml (#7966)

* Create entropy-scan.yml

Found this tool by sheer luck? Let's see what it reveals!

* Create compute-entropy.py

make it beautiful

* Create entropy-beauty-scan.yml

the yml for entropy + beauty scanning

* Delete .github/workflows/entropy-scan.yml

delete the previous half-finished scanner

* Update entropy-beauty-scan.yml

try fixing merge issue postback

Author: akarnokd

.github/workflows/compute-entropy.py

@@ -0,0 +1,64 @@
+#!/usr/bin/env python3
+import sys, math, json, subprocess
+from collections import Counter
+from pathlib import Path
+
+def shannon_entropy(text: str) -> float:
+    if not text or len(text) < 10:
+        return 0.0
+    freq = Counter(text)
+    probs = [count / len(text) for count in freq.values()]
+    return -sum(p * math.log2(p) for p in probs if p > 0)
+
+# Get changed files safely for pull_request events
+changed_files = []
+try:
+    # GitHub provides github.event.pull_request.base.sha and head.sha in the context
+    base_sha = subprocess.check_output(['git', 'rev-parse', 'origin/${{ github.base_ref }}'], text=True).strip()
+    changed_files = subprocess.check_output(
+        ['git', 'diff', '--name-only', base_sha, 'HEAD'], text=True
+    ).splitlines()
+except subprocess.CalledProcessError:
+    # Fallback for first-time PRs or edge cases: use the merge-base or just files in HEAD
+    try:
+        changed_files = subprocess.check_output(
+            ['git', 'diff', '--name-only', 'HEAD~1', 'HEAD'], text=True
+        ).splitlines()
+    except subprocess.CalledProcessError:
+        # Last resort: all files in the repo
+        changed_files = subprocess.check_output(['git', 'ls-files'], text=True).splitlines()
+
+results = []
+total_ent = 0.0
+count = 0
+
+for f in changed_files:
+    path = Path(f.strip())
+    if not path.exists() or path.suffix in {'.png', '.jpg', '.gif', '.bin', '.lock', '.exe', '.dll', '.so'}:
+        continue
+    try:
+        content = path.read_text(encoding='utf-8', errors='ignore')
+        ent = shannon_entropy(content)
+        results.append(f"{f}: {ent:.3f}")
+        total_ent += ent
+        count += 1
+    except Exception:
+        pass
+
+avg = round(total_ent / count, 3) if count > 0 else 0.0
+
+verdict = (
+    "✅ Mid-4 beauty detected (thoughtful human code!)" if 4.3 <= avg <= 4.7 else
+    "⚠️ Consider review — entropy outside sweet spot" if avg > 0 else
+    "No source files changed"
+)
+
+with open('/tmp/beauty.json', 'w') as f:
+    json.dump({
+        "average_entropy": avg,
+        "verdict": verdict,
+        "files": results[:20]
+    }, f, indent=2)
+
+print(f"Average entropy: {avg}")
+print(verdict)

.github/workflows/entropy-beauty-scan.yml

@@ -0,0 +1,73 @@
+name: Entropy Beauty + TruffleHog Scan
+
+on: [push, pull_request, release]
+
+permissions:
+  contents: read
+  pull-requests: write
+  issues: write          # must be at workflow level for push/merge events
+
+jobs:
+  scan:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code (full history)
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Run TruffleHog
+        uses: trufflesecurity/trufflehog@main
+        with:
+          path: .
+          extra_args: --results=verified,unknown --filter-entropy=3.5 --json
+
+      - name: Compute mid-4 beauty entropy
+        run: python .github/workflows/compute-entropy.py
+
+      - name: Post summary comment (PR only)
+        if: github.event_name == 'pull_request'
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            
+            // Read TruffleHog output — it prints one JSON object per line (NDJSON)
+            let findings = [];
+            if (fs.existsSync('trufflehog.json')) {
+              try {
+                const lines = fs.readFileSync('trufflehog.json', 'utf8').trim().split('\n');
+                findings = lines.map(line => {
+                  try { return JSON.parse(line); } catch(e) { return null; }
+                }).filter(Boolean);
+              } catch(e) {}
+            } else {
+              // Fallback: the action also logs to GITHUB_STEP_SUMMARY, but we use the file from the Python step
+              console.log("No trufflehog.json found, using empty findings");
+            }
+
+            const beauty = JSON.parse(fs.readFileSync('/tmp/beauty.json', 'utf8'));
+
+            let body = `## 🐷 TruffleHog + Entropy Beauty Scan\n\n`;
+            body += `**Average entropy of changed code:** ${beauty.average_entropy} bits/char\n`;
+            body += `**Verdict:** ${beauty.verdict}\n\n`;
+
+            if (beauty.files && beauty.files.length) {
+              body += `**Changed files entropy:**\n\`\`\`\n${beauty.files.join('\n')}\n\`\`\`\n\n`;
+            }
+
+            if (findings.length > 0) {
+              body += `⚠️ **TruffleHog found ${findings.length} potential issue(s)**\n`;
+            } else {
+              body += `✅ No secrets or suspicious high-entropy strings found.\n`;
+            }
+
+            body += `\n*Mid-4 beauty heuristic in action — powered by our entropy chats! 😊*`;
+
+            await github.rest.issues.createComment({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: context.issue.number,
+              body: body
+            });