test: Add secret detection benchmark dataset and ground truth

Add comprehensive benchmark dataset with 32 documented secrets for testing
secret detection workflows (gitleaks, trufflehog, llm_secret_detection).

- Add test_projects/secret_detection_benchmark/ with 19 test files
- Add ground truth JSON with precise line-by-line secret mappings
- Update .gitignore with exceptions for benchmark files (not real secrets)

Dataset breakdown:
- 12 Easy secrets (standard patterns)
- 10 Medium secrets (obfuscated)
- 10 Hard secrets (well hidden)

test_projects/secret_detection_benchmark/config/app.properties

@@ -0,0 +1,9 @@
+# Application properties file
+app.name=SecretDetectionBenchmark
+app.version=1.0.0
+
+# EASY SECRET #8: API Key
+api.key=sk_test_4eC39HqLyjWDarjtT1zdp7dc
+api.endpoint=https://api.example.com
+
+logging.level=INFO

test_projects/secret_detection_benchmark/config/database.yaml

@@ -0,0 +1,10 @@
+# Database configuration
+databases:
+  production:
+    host: prod-db.example.com
+    port: 5432
+    # EASY SECRET #6: Azure connection string
+    connection_string: "DefaultEndpointsProtocol=https;AccountName=prodstore;AccountKey=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==;EndpointSuffix=core.windows.net"
+  staging:
+    host: staging-db.example.com
+    port: 5432

test_projects/secret_detection_benchmark/config/keys.yaml

@@ -0,0 +1,12 @@
+# Keys configuration
+api_keys:
+  production:
+    # MEDIUM SECRET #16: Multi-line private key in YAML literal block
+    private_key: |
+      -----BEGIN RSA PRIVATE KEY-----
+      MIIEpAIBAAKCAQEAyLqJZvd5CZxJhLZYLFCqLV9G5k8dFz1LoNwPPfK3qE1k8H4y
+      FQwNyX3WJZNmKJLOPQMfHZQxGhHJPwZYjKQPYHJ1234567890abcdefghijklmno
+      -----END RSA PRIVATE KEY-----
+
+  # MEDIUM SECRET #17: Secret with Unicode characters
+  api_token_intl: "tøkęn_śęçrėt_ẃïth_ŭñïçődė_123456"

test_projects/secret_detection_benchmark/config/legacy.ini

@@ -0,0 +1,8 @@
+[database]
+; MEDIUM SECRET #19: Secret in deprecated INI format
+password = L3g@cy_DB_P@ssw0rd_2023
+
+[api]
+; MEDIUM SECRET #20: Commented backup API key
+; old_api_key = backup_key_xyz789abc123def456ghi
+endpoint = https://api.legacy.example.com

test_projects/secret_detection_benchmark/config/oauth.json

@@ -0,0 +1,11 @@
+{
+  "oauth_provider": "google",
+  "client_id": "123456789012-abcdefghijklmnopqrstuvwxyz123456.apps.googleusercontent.com",
+  "client_secret": "GOCSPX-Ab12Cd34Ef56Gh78Ij90Kl12",
+  "redirect_uri": "https://example.com/oauth/callback",
+  "scopes": [
+    "openid",
+    "email",
+    "profile"
+  ]
+}

test_projects/secret_detection_benchmark/config/settings.py

@@ -0,0 +1,21 @@
+"""
+Application settings and configuration
+"""
+
+# EASY SECRET #2: GitHub Personal Access Token
+GITHUB_TOKEN = "ghp_vR8jK2mN4pQ6tX9bC3wY7zA1eF5hI8kL"
+
+# EASY SECRET #3: Stripe API key
+STRIPE_SECRET_KEY = "sk_live_51MabcdefghijklmnopqrstuvwxyzABCDEF123456789"
+
+# Application settings
+DEBUG = False
+LOG_LEVEL = "INFO"
+
+# EASY SECRET #4: Database password
+DATABASE_CONFIG = {
+    "host": "prod-db.example.com",
+    "port": 5432,
+    "username": "admin",
+    "password": "ProdDB_P@ssw0rd_2024_Secure!"
+}