semantica/.github/workflows/security-scan.yml

name: Security Scan

on:
  schedule:
    - cron: '30 1 * * 1,4'  # Mon/Thu 7 AM IST
  push:
    branches: [main]
    paths-ignore:
      - 'docs/**'
      - 'mkdocs.yml'
      - 'requirements-docs.txt'
      - '**/*.md'
  pull_request:
    branches: [main]
    paths-ignore:
      - 'docs/**'
      - 'mkdocs.yml'
      - 'requirements-docs.txt'
      - '**/*.md'

jobs:
  security-scan:
    runs-on: ubuntu-latest
    permissions:
      contents: read
      security-events: write
      actions: read
    
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
      
      - name: Set up Python
        uses: actions/setup-python@v4
        with:
          python-version: '3.11'
        
      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install safety bandit semgrep jq
        
      - name: Run Safety Check (Package Vulnerabilities)
        run: |
          safety check --json --output safety-report.json || true
          echo "Checking for package vulnerabilities..."
          
          # Count vulnerabilities safely
          VULNS=$(safety check --json --output /dev/stdout 2>/dev/null | jq '.vulnerabilities | length' 2>/dev/null || echo "0")
          
          if [ "$VULNS" -gt 0 ]; then
            echo "❌ Security vulnerabilities found: $VULNS"
            echo "CI will fail to prevent merging of vulnerable dependencies"
            echo ""
            echo "Vulnerability details:"
            safety check || true
            exit 1
          else
            echo "✅ No security vulnerabilities found"
          fi
        
      - name: Run Bandit (Code Security Linter)
        run: |
          bandit -r semantica/ -f json -o bandit-report.json || true
          echo "Checking for HIGH severity security issues..."
          
          # Count HIGH severity issues
          HIGH_ISSUES=$(bandit -r semantica/ -f json -ll 2>/dev/null | jq -r '.results[]? | select(.issue_severity == "HIGH") | .test_name' 2>/dev/null | wc -l || echo "0")
          
          if [ "$HIGH_ISSUES" -gt 0 ]; then
            echo "❌ HIGH severity security issues found: $HIGH_ISSUES"
            echo "CI will fail to prevent merging of high-risk code"
            echo ""
            echo "High severity issues:"
            bandit -r semantica/ -ll | grep "Severity: High" -A 5 -B 1 || true
            exit 1
          else
            echo "✅ No HIGH severity security issues found"
          fi
        
      - name: Run Semgrep (Static Analysis)
        run: |
          echo "Running Semgrep static analysis..."
          semgrep --config=auto --json --output=semgrep-report.json semantica/ || true
          
          # Run security-focused rules
          echo "Checking for security patterns..."
          SECURITY_ISSUES=$(semgrep --config=p/security --json semantica/ 2>/dev/null | jq '.results | length' 2>/dev/null || echo "0")
          
          if [ "$SECURITY_ISSUES" -gt 0 ]; then
            echo "⚠️ Security patterns found: $SECURITY_ISSUES"
            echo "Review these findings for potential improvements"
            semgrep --config=p/security semantica/ || true
          else
            echo "✅ No security patterns found"
          fi
        
      - name: Upload Security Reports
        uses: actions/upload-artifact@v7
        with:
          name: security-reports
          path: |
            safety-report.json
            bandit-report.json
            semgrep-report.json
        
      - name: Comment PR with Security Results
        if: github.event_name == 'pull_request'
        uses: actions/github-script@v8
        with:
          script: |
            const fs = require('fs');
            
            // Read safety report
            let safetyResults = '';
            try {
              const safetyData = JSON.parse(fs.readFileSync('safety-report.json', 'utf8'));
              if (safetyData.vulnerabilities && safetyData.vulnerabilities.length > 0) {
                safetyResults = `## Safety Vulnerabilities Found\\n`;
                safetyData.vulnerabilities.forEach(vuln => {
                  safetyResults += `- **${vuln.package}**: ${vuln.advisory}\\n`;
                });
              } else {
                safetyResults = '## No Safety Vulnerabilities Found\\n';
              }
            } catch (e) {
              safetyResults = '## Safety scan completed\\n';
            }
            
            // Read bandit report
            let banditResults = '';
            try {
              const banditData = JSON.parse(fs.readFileSync('bandit-report.json', 'utf8'));
              if (banditData.results && banditData.results.length > 0) {
                const highIssues = banditData.results.filter(issue => issue.issue_severity === 'HIGH');
                if (highIssues.length > 0) {
                  banditResults = `## High Severity Security Issues Found\\n`;
                  highIssues.forEach(issue => {
                    banditResults += `- **${issue.test_name}**: ${issue.filename}:${issue.line_number}\\n`;
                  });
                } else {
                  banditResults = '## No High Severity Security Issues Found\\n';
                }
              } else {
                banditResults = '## No Bandit Issues Found\\n';
              }
            } catch (e) {
              banditResults = '## Bandit scan completed\\n';
            }
            
            // Read semgrep report
            let semgrepResults = '';
            try {
              const semgrepData = JSON.parse(fs.readFileSync('semgrep-report.json', 'utf8'));
              if (semgrepData.results && semgrepData.results.length > 0) {
                semgrepResults = `## Security Patterns Found\\n`;
                semgrepData.results.slice(0, 10).forEach(issue => {
                  semgrepResults += `- **${issue.rule_id}**: ${issue.path}\\n`;
                });
                if (semgrepData.results.length > 10) {
                  semgrepResults += `- ... and ${semgrepData.results.length - 10} more\\n`;
                }
              } else {
                semgrepResults = '## No Security Patterns Found\\n';
              }
            } catch (e) {
              semgrepResults = '## Semgrep scan completed\\n';
            }
            
            // Create summary comment
            const comment = `# 🔒 Security Scan Results\\n\\n${safetyResults}\\n\\n${banditResults}\\n\\n${semgrepResults}\\n\\n---\\n\\n*This security scan runs automatically on source-code PRs and bi-weekly (skipped for doc/markdown-only changes).*\\n\\n📊 **Security Policy**: CI fails on vulnerabilities and HIGH severity issues.`;
            
            // Post comment with error handling
            try {
              await github.rest.issues.createComment({
                issue_number: context.issue.number,
                owner: context.repo.owner,
                repo: context.repo.repo,
                body: comment
              });
              console.log('✅ Security comment posted successfully');
            } catch (error) {
              console.log('⚠️ Could not post security comment:', error.message);
              console.log('📋 Security scan results saved to artifacts');
            }