@synapta/skills 0.1.0 → 0.1.2

package/skills/secret-hygiene/assets/config-custom.toml

@@ -0,0 +1,178 @@
+# Gitleaks Custom Configuration Template
+# Use this as a starting point for organization-specific detection rules
+
+title = "Custom Gitleaks Configuration"
+
+[extend]
+# Extend default Gitleaks rules with custom rules
+useDefault = true
+
+# =============================================================================
+# GLOBAL ALLOWLIST
+# =============================================================================
+# Global allowlists apply to ALL rules and have highest precedence
+
+[allowlist]
+description = "Global allowlist for organization-wide exceptions"
+
+# Paths to exclude from scanning
+paths = [
+  # Test and documentation
+  '''test/.*''',
+  '''docs?/.*''',
+  '''examples?/.*''',
+
+  # Dependencies
+  '''node_modules/.*''',
+  '''vendor/.*''',
+
+  # Build artifacts
+  '''dist/.*''',
+  '''build/.*''',
+]
+
+# Known placeholder values
+stopwords = [
+  "example",
+  "placeholder",
+  "your_key_here",
+  "test",
+  "mock",
+  "dummy",
+]
+
+# Public non-secrets
+regexes = [
+  '''-----BEGIN CERTIFICATE-----''',
+  '''-----BEGIN PUBLIC KEY-----''',
+]
+
+# Manually verified commits (add with explanatory comments)
+commits = []
+
+# =============================================================================
+# CUSTOM DETECTION RULES
+# =============================================================================
+# Add organization-specific secret patterns here
+
+# Example: Custom API Key Pattern
+[[rules]]
+id = "acme-corp-api-key"
+description = "ACME Corp Internal API Key"
+# Regex pattern to match your organization's API key format
+# Use triple-quoted strings for complex patterns
+regex = '''(?i)acme[_-]?api[_-]?key[\s]*[=:][\s]*['"]?([a-zA-Z0-9]{40})['"]?'''
+# Capture group containing the actual secret (for entropy analysis)
+secretGroup = 1
+# Tags for categorization and filtering
+tags = ["api-key", "acme-internal"]
+
+# Optional: Rule-specific allowlist (lower precedence than global)
+#[rules.allowlist]
+#paths = ['''config/defaults\.yaml''']
+#stopwords = ["DEFAULT_KEY"]
+
+# Example: Custom Database Password Pattern
+[[rules]]
+id = "acme-corp-db-password"
+description = "ACME Corp Database Password Format"
+# Matches company-specific password format
+regex = '''(?i)(db_pass|database_password)[\s]*[=:][\s]*['"]([A-Z][a-z0-9@#$%]{15,})['"]'''
+secretGroup = 2
+tags = ["password", "database", "acme-internal"]
+
+# Example: High-Entropy Detection with Custom Threshold
+[[rules]]
+id = "high-entropy-string"
+description = "High entropy string (potential secret)"
+# Match strings of 32+ alphanumeric characters
+regex = '''[a-zA-Z0-9+/]{32,}'''
+# Shannon entropy threshold (0.0 - 8.0, higher = more random)
+entropy = 4.5
+# Which capture group to analyze (0 = entire match)
+secretGroup = 0
+tags = ["entropy", "generic"]
+
+[rules.allowlist]
+# Allowlist base64-encoded images
+regexes = ['''data:image/[^;]+;base64,''']
+
+# Example: Custom Service Account Key
+[[rules]]
+id = "acme-corp-service-account"
+description = "ACME Corp Service Account JSON Key"
+# Detect JSON structure with specific fields
+regex = '''"type":\s*"acme_service_account"'''
+tags = ["service-account", "acme-internal"]
+
+# Example: Custom OAuth Token Format
+[[rules]]
+id = "acme-corp-oauth-token"
+description = "ACME Corp OAuth Token"
+# Custom token format: acme_oauth_v1_<40 hex chars>
+regex = '''acme_oauth_v1_[a-f0-9]{40}'''
+tags = ["oauth", "token", "acme-internal"]
+
+# =============================================================================
+# TESTING CUSTOM RULES
+# =============================================================================
+# Test your custom rules with:
+#   gitleaks detect --config config-custom.toml -v
+#
+# Test against specific file:
+#   gitleaks detect --config config-custom.toml --source path/to/file --no-git
+#
+# Test regex pattern online:
+#   https://regex101.com/ (select Golang flavor)
+#
+# =============================================================================
+
+# =============================================================================
+# ENTROPY ANALYSIS GUIDE
+# =============================================================================
+# Entropy values (Shannon entropy):
+#   0.0 - 2.5: Very low (repeated characters, simple patterns)
+#   2.5 - 3.5: Low (common words, simple sequences)
+#   3.5 - 4.5: Medium (mixed case, some randomness)
+#   4.5 - 5.5: High (strong randomness, likely secret)
+#   5.5 - 8.0: Very high (cryptographic randomness)
+#
+# Recommended thresholds:
+#   - API keys: 4.5+
+#   - Passwords: 3.5+
+#   - Tokens: 4.5+
+#   - Generic secrets: 5.0+
+# =============================================================================
+
+# =============================================================================
+# REGEX CAPTURE GROUPS
+# =============================================================================
+# Use capture groups to extract the actual secret from surrounding text:
+#
+#   regex = '''api_key\s*=\s*"([a-zA-Z0-9]+)"'''
+#                                 ^^^^^^^^^
+#                                 Group 1
+#
+#   secretGroup = 1  # Analyze only the key value, not 'api_key = ""'
+#
+# This improves entropy analysis accuracy and reduces false positives.
+# =============================================================================
+
+# =============================================================================
+# COMPOSITE RULES (Advanced)
+# =============================================================================
+# Gitleaks v8.28.0+ supports composite rules for context-aware detection
+# Useful for secrets that require nearby context (multi-line patterns)
+
+#[[rules]]
+#id = "composite-api-key"
+#description = "API key with usage context"
+#regex = '''api_key\s*='''
+#
+#[[rules.composite]]
+#pattern = '''initialize_client'''
+#location = "line"  # "line", "fragment", or "commit"
+#distance = 5       # Within 5 lines
+#
+# This detects api_key = "..." only when "initialize_client" appears within 5 lines
+# =============================================================================

package/skills/secret-hygiene/assets/config-strict.toml

@@ -0,0 +1,48 @@
+# Gitleaks Strict Configuration
+# High-sensitivity detection with minimal allowlisting
+# Use for: Security-critical repositories, financial services, healthcare
+
+title = "Gitleaks Strict Configuration"
+
+[extend]
+# Use all default Gitleaks rules
+useDefault = true
+
+[allowlist]
+description = "Minimal allowlist - only proven false positives"
+
+# Only allow in build artifacts and dependencies
+paths = [
+  '''node_modules/.*''',
+  '''vendor/.*''',
+  '''\.min\.js$''',
+  '''\.min\.css$''',
+]
+
+# Only obvious non-secret patterns
+stopwords = [
+  "EXAMPLE_DO_NOT_USE",
+  "PLACEHOLDER_REPLACE_ME",
+]
+
+# All commits must be manually verified before allowlisting
+commits = []
+
+# Additional strict rules for high-value targets
+
+[[rules]]
+id = "strict-env-file"
+description = "Detect any .env files (should not be in repo)"
+regex = '''.*'''
+path = '''\.env$'''
+tags = ["env-file", "strict"]
+
+[[rules]]
+id = "strict-config-secrets"
+description = "Config files with potential secrets"
+regex = '''(?i)(password|secret|key|token|credential)[\s]*[=:][\s]*['"]?([a-zA-Z0-9!@#$%^&*()_+\-=\[\]{};':"\\|,.<>\/?]{8,})['"]?'''
+secretGroup = 2
+tags = ["config", "strict"]
+[rules.allowlist]
+paths = ['''test/.*''']
+stopwords = ["EXAMPLE"]

package/skills/secret-hygiene/assets/github-action.yml

@@ -0,0 +1,181 @@
+# GitHub Actions Workflow for Gitleaks Secret Scanning
+# Save as: .github/workflows/gitleaks.yml
+
+name: Secret Scanning with Gitleaks
+
+on:
+  push:
+    branches:
+      - main
+      - develop
+      - 'release/**'
+  pull_request:
+    branches:
+      - main
+      - develop
+  schedule:
+    # Run daily at 2 AM UTC
+    - cron: '0 2 * * *'
+  workflow_dispatch:  # Allow manual triggers
+
+# Cancel in-progress runs when new commit pushed
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  gitleaks-scan:
+    name: Scan for Secrets
+    runs-on: ubuntu-latest
+
+    permissions:
+      # Required for uploading SARIF results to GitHub Security tab
+      security-events: write
+      # Required for checking out private repos
+      contents: read
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+        with:
+          # Fetch full history for comprehensive scanning
+          fetch-depth: 0
+
+      - name: Run Gitleaks Scan
+        id: gitleaks
+        uses: gitleaks/gitleaks-action@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          # Optional: Use custom configuration
+          # GITLEAKS_CONFIG: .gitleaks.toml
+
+      # Optional: Generate JSON report for further processing
+      - name: Generate JSON Report
+        if: always()  # Run even if secrets found
+        run: |
+          docker run --rm -v ${{ github.workspace }}:/repo \
+            zricethezav/gitleaks:latest \
+            detect --source /repo \
+            --report-path /repo/gitleaks-report.json \
+            --report-format json \
+            --exit-code 0 || true
+
+      # Optional: Upload JSON report as artifact
+      - name: Upload Scan Report
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: gitleaks-report
+          path: gitleaks-report.json
+          retention-days: 30
+
+      # Optional: Generate SARIF report for GitHub Security tab
+      - name: Generate SARIF Report
+        if: always()
+        run: |
+          docker run --rm -v ${{ github.workspace }}:/repo \
+            zricethezav/gitleaks:latest \
+            detect --source /repo \
+            --report-path /repo/gitleaks.sarif \
+            --report-format sarif \
+            --exit-code 0 || true
+
+      # Optional: Upload SARIF report to GitHub Security
+      - name: Upload SARIF to GitHub Security
+        if: always()
+        uses: github/codeql-action/upload-sarif@v3
+        with:
+          sarif_file: gitleaks.sarif
+          category: gitleaks
+
+      # Optional: Comment on PR with findings
+      - name: Comment PR with Findings
+        if: failure() && github.event_name == 'pull_request'
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const fs = require('fs');
+            try {
+              const report = JSON.parse(fs.readFileSync('gitleaks-report.json', 'utf8'));
+              const findings = report.length;
+
+              const comment = `## 🔒 Secret Scanning Results
+
+              ⚠️ **${findings} potential secret(s) detected!**
+
+              Please review the findings and take immediate action:
+              1. **Do not merge** this PR until secrets are removed
+              2. Rotate any exposed credentials immediately
+              3. Remove secrets from code and use environment variables
+              4. Review the security tab for detailed findings
+
+              See [Secret Scanning Guide](https://github.com/${{ github.repository }}/blob/main/docs/secret-scanning.md) for remediation steps.`;
+
+              github.rest.issues.createComment({
+                issue_number: context.issue.number,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: comment
+              });
+            } catch (error) {
+              console.log('No report file or error reading it:', error.message);
+            }
+
+      # Optional: Post to Slack on failure
+      - name: Notify Slack on Failure
+        if: failure()
+        uses: slackapi/slack-github-action@v1
+        with:
+          payload: |
+            {
+              "text": "🚨 Secrets detected in ${{ github.repository }}",
+              "blocks": [
+                {
+                  "type": "section",
+                  "text": {
+                    "type": "mrkdwn",
+                    "text": "*Secret Scanning Alert*\n\nSecrets detected in repository: `${{ github.repository }}`\nBranch: `${{ github.ref_name }}`\nCommit: `${{ github.sha }}`\n\n<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|View Details>"
+                  }
+                }
+              ]
+            }
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
+          SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
+
+  # Optional: Baseline scanning for incremental detection
+  baseline-scan:
+    name: Incremental Scan Against Baseline
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push'
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Download Existing Baseline
+        continue-on-error: true
+        run: |
+          # Download baseline from artifact storage or S3
+          # Example: aws s3 cp s3://bucket/.gitleaks-baseline.json .
+          echo "Baseline download would go here"
+
+      - name: Run Incremental Scan
+        run: |
+          docker run --rm -v ${{ github.workspace }}:/repo \
+            zricethezav/gitleaks:latest \
+            detect --source /repo \
+            --baseline-path /repo/.gitleaks-baseline.json \
+            --report-path /repo/new-findings.json \
+            --report-format json \
+            --exit-code 1 || true
+
+      - name: Upload New Findings
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: new-findings
+          path: new-findings.json
+          retention-days: 90

package/skills/secret-hygiene/assets/gitlab-ci.yml

@@ -0,0 +1,257 @@
+# GitLab CI Pipeline for Gitleaks Secret Scanning
+# Save as: .gitlab-ci.yml or include in existing pipeline
+
+# Define stages
+stages:
+  - security
+  - report
+
+# Default Docker image for security jobs
+image: docker:latest
+
+services:
+  - docker:dind
+
+variables:
+  # Gitleaks Docker image
+  GITLEAKS_IMAGE: zricethezav/gitleaks:latest
+  # Report output path
+  REPORT_PATH: gitleaks-report.json
+  # SARIF output for GitLab Security Dashboard
+  SARIF_PATH: gl-secret-detection-report.json
+
+# Secret scanning job
+gitleaks-scan:
+  stage: security
+  image: $GITLEAKS_IMAGE
+
+  # Run on all branches and merge requests
+  rules:
+    - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
+    - if: '$CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH'
+    - if: '$CI_COMMIT_BRANCH =~ /^(develop|release)/'
+
+  script:
+    # Run Gitleaks scan
+    - echo "Running Gitleaks secret detection..."
+    - |
+      gitleaks detect \
+        --source . \
+        --report-path $REPORT_PATH \
+        --report-format json \
+        --verbose || true
+
+    # Convert to GitLab SARIF format for Security Dashboard
+    - |
+      gitleaks detect \
+        --source . \
+        --report-path $SARIF_PATH \
+        --report-format sarif \
+        --verbose || true
+
+    # Check if secrets were found
+    - |
+      if [ -s "$REPORT_PATH" ] && [ "$(cat $REPORT_PATH)" != "null" ]; then
+        echo "⚠️  Secrets detected! Review findings below."
+        cat $REPORT_PATH | jq -r '.[] | "File: \(.File)\nLine: \(.StartLine)\nRule: \(.RuleID)\n"'
+        exit 1
+      else
+        echo "✅ No secrets detected"
+      fi
+
+  artifacts:
+    paths:
+      - $REPORT_PATH
+      - $SARIF_PATH
+    reports:
+      # GitLab Security Dashboard integration
+      secret_detection: $SARIF_PATH
+    when: always
+    expire_in: 30 days
+
+  # Allow failure for initial rollout, then set to false
+  allow_failure: false
+
+# Optional: Incremental scanning with baseline
+gitleaks-incremental:
+  stage: security
+  image: $GITLEAKS_IMAGE
+
+  # Only run on merge requests
+  rules:
+    - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
+
+  script:
+    # Download baseline from artifacts or storage
+    - echo "Downloading baseline..."
+    - |
+      if [ -f ".gitleaks-baseline.json" ]; then
+        echo "Using baseline from repository"
+      else
+        echo "No baseline found, running full scan"
+      fi
+
+    # Run incremental scan
+    - |
+      if [ -f ".gitleaks-baseline.json" ]; then
+        gitleaks detect \
+          --source . \
+          --baseline-path .gitleaks-baseline.json \
+          --report-path new-findings.json \
+          --report-format json \
+          --exit-code 1 || true
+
+        if [ -s "new-findings.json" ] && [ "$(cat new-findings.json)" != "null" ]; then
+          echo "⚠️  New secrets detected since baseline!"
+          cat new-findings.json | jq .
+          exit 1
+        fi
+      fi
+
+  artifacts:
+    paths:
+      - new-findings.json
+    when: always
+    expire_in: 7 days
+
+# Optional: Create baseline on main branch
+create-baseline:
+  stage: security
+  image: $GITLEAKS_IMAGE
+
+  # Only run on main/master branch
+  rules:
+    - if: '$CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH'
+      when: manual  # Manual trigger to avoid overwriting
+
+  script:
+    - echo "Creating new baseline..."
+    - |
+      gitleaks detect \
+        --source . \
+        --report-path .gitleaks-baseline.json \
+        --report-format json \
+        --exit-code 0 || true
+
+  artifacts:
+    paths:
+      - .gitleaks-baseline.json
+    expire_in: 365 days
+
+# Optional: Generate human-readable report
+generate-report:
+  stage: report
+  image: python:3.11-slim
+
+  dependencies:
+    - gitleaks-scan
+
+  rules:
+    - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
+    - if: '$CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH'
+
+  script:
+    - pip install jinja2
+    - |
+      python3 << 'EOF'
+      import json
+      import sys
+      from datetime import datetime
+
+      try:
+          with open('gitleaks-report.json', 'r') as f:
+              findings = json.load(f)
+
+          if not findings:
+              print("✅ No secrets detected")
+              sys.exit(0)
+
+          print("# Gitleaks Secret Detection Report")
+          print(f"\n**Generated**: {datetime.now().isoformat()}")
+          print(f"**Total Findings**: {len(findings)}\n")
+
+          for idx, finding in enumerate(findings, 1):
+              print(f"\n## Finding {idx}")
+              print(f"- **File**: {finding.get('File', 'unknown')}")
+              print(f"- **Line**: {finding.get('StartLine', 'unknown')}")
+              print(f"- **Rule**: {finding.get('RuleID', 'unknown')}")
+              print(f"- **Description**: {finding.get('Description', 'unknown')}")
+              print(f"- **Commit**: {finding.get('Commit', 'N/A')}\n")
+
+      except FileNotFoundError:
+          print("No report file found")
+      except json.JSONDecodeError:
+          print("No findings in report")
+      EOF
+
+  artifacts:
+    paths:
+      - gitleaks-report.json
+
+# Optional: Comment on merge request
+comment-mr:
+  stage: report
+  image: alpine:latest
+
+  dependencies:
+    - gitleaks-scan
+
+  rules:
+    - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
+
+  before_script:
+    - apk add --no-cache curl jq
+
+  script:
+    - |
+      if [ -s "$REPORT_PATH" ] && [ "$(cat $REPORT_PATH)" != "null" ]; then
+        FINDING_COUNT=$(cat $REPORT_PATH | jq '. | length')
+
+        COMMENT="## 🔒 Secret Scanning Results\n\n"
+        COMMENT="${COMMENT}⚠️ **${FINDING_COUNT} potential secret(s) detected!**\n\n"
+        COMMENT="${COMMENT}Please review the findings and take immediate action:\n"
+        COMMENT="${COMMENT}1. **Do not merge** this MR until secrets are removed\n"
+        COMMENT="${COMMENT}2. Rotate any exposed credentials immediately\n"
+        COMMENT="${COMMENT}3. Remove secrets from code and use CI/CD variables\n\n"
+        COMMENT="${COMMENT}See pipeline artifacts for detailed findings."
+
+        # Post comment to merge request
+        curl --request POST \
+          --header "PRIVATE-TOKEN: $GITLAB_TOKEN" \
+          --data-urlencode "body=$COMMENT" \
+          "$CI_API_V4_URL/projects/$CI_PROJECT_ID/merge_requests/$CI_MERGE_REQUEST_IID/notes"
+      fi
+
+  allow_failure: true
+
+# Optional: Scheduled nightly scan
+nightly-scan:
+  stage: security
+  image: $GITLEAKS_IMAGE
+
+  # Run on schedule only
+  rules:
+    - if: '$CI_PIPELINE_SOURCE == "schedule"'
+
+  script:
+    - echo "Running comprehensive nightly secret scan..."
+    - |
+      gitleaks detect \
+        --source . \
+        --report-path nightly-scan.json \
+        --report-format json \
+        --verbose
+
+  artifacts:
+    paths:
+      - nightly-scan.json
+    when: always
+    expire_in: 90 days
+
+  # Send notifications on failure
+  after_script:
+    - |
+      if [ $? -ne 0 ]; then
+        echo "Secrets detected in nightly scan!"
+        # Add notification logic (email, Slack, etc.)
+      fi