mirror of
https://github.com/FuzzingLabs/fuzzforge_ai.git
synced 2026-07-09 20:58:40 +02:00
feat: Add secret detection workflows and comprehensive benchmarking (#15)
Add three production-ready secret detection workflows with full benchmarking infrastructure: **New Workflows:** - gitleaks_detection: Pattern-based secret scanning (13/32 benchmark secrets) - trufflehog_detection: Entropy-based detection with verification (1/32 benchmark secrets) - llm_secret_detection: AI-powered semantic analysis (32/32 benchmark secrets - 100% recall) **Benchmarking Infrastructure:** - Ground truth dataset with 32 documented secrets (12 Easy, 10 Medium, 10 Hard) - Automated comparison tools for precision/recall testing - SARIF output format for all workflows - Performance metrics and tool comparison reports **Fixes:** - Set gitleaks default to no_git=True for uploaded directories - Update documentation with correct secret counts and workflow names - Temporarily deactivate AI agent command - Clean up deprecated test files and GitGuardian workflow **Testing:** All workflows verified on secret_detection_benchmark and vulnerable_app test projects. Workers healthy and system fully functional.
This commit is contained in:
tduhamel42
@@ -0,0 +1,13 @@
|
||||
"""
|
||||
TruffleHog Detection Workflow
|
||||
"""
|
||||
|
||||
# Copyright (c) 2025 FuzzingLabs
|
||||
#
|
||||
# Licensed under the Business Source License 1.1 (BSL). See the LICENSE file
|
||||
# at the root of this repository for details.
|
||||
|
||||
from .workflow import TrufflehogDetectionWorkflow
|
||||
from .activities import scan_with_trufflehog, trufflehog_generate_sarif
|
||||
|
||||
__all__ = ["TrufflehogDetectionWorkflow", "scan_with_trufflehog", "trufflehog_generate_sarif"]
|
||||
@@ -0,0 +1,111 @@
|
||||
"""TruffleHog Detection Workflow Activities"""
|
||||
|
||||
import logging
|
||||
from pathlib import Path
|
||||
from typing import Dict, Any
|
||||
from temporalio import activity
|
||||
|
||||
try:
|
||||
from toolbox.modules.secret_detection.trufflehog import TruffleHogModule
|
||||
except ImportError:
|
||||
from modules.secret_detection.trufflehog import TruffleHogModule
|
||||
|
||||
@activity.defn(name="scan_with_trufflehog")
|
||||
async def scan_with_trufflehog(target_path: str, config: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""Scan code using TruffleHog."""
|
||||
activity.logger.info(f"Starting TruffleHog scan: {target_path}")
|
||||
workspace = Path(target_path)
|
||||
|
||||
trufflehog = TruffleHogModule()
|
||||
trufflehog.validate_config(config)
|
||||
result = await trufflehog.execute(config, workspace)
|
||||
|
||||
if result.status == "failed":
|
||||
raise RuntimeError(f"TruffleHog scan failed: {result.error}")
|
||||
|
||||
findings_dicts = [finding.model_dump() for finding in result.findings]
|
||||
return {"findings": findings_dicts, "summary": result.summary}
|
||||
|
||||
|
||||
@activity.defn(name="trufflehog_generate_sarif")
|
||||
async def trufflehog_generate_sarif(findings: list, metadata: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Generate SARIF report from TruffleHog findings.
|
||||
|
||||
Args:
|
||||
findings: List of finding dictionaries
|
||||
metadata: Metadata including tool_name, tool_version
|
||||
|
||||
Returns:
|
||||
SARIF report dictionary
|
||||
"""
|
||||
activity.logger.info(f"Generating SARIF report from {len(findings)} findings")
|
||||
|
||||
# Basic SARIF 2.1.0 structure
|
||||
sarif_report = {
|
||||
"version": "2.1.0",
|
||||
"$schema": "https://raw.githubusercontent.com/oasis-tcs/sarif-spec/master/Schemata/sarif-schema-2.1.0.json",
|
||||
"runs": [
|
||||
{
|
||||
"tool": {
|
||||
"driver": {
|
||||
"name": metadata.get("tool_name", "trufflehog"),
|
||||
"version": metadata.get("tool_version", "3.63.2"),
|
||||
"informationUri": "https://github.com/trufflesecurity/trufflehog"
|
||||
}
|
||||
},
|
||||
"results": []
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
# Convert findings to SARIF results
|
||||
for finding in findings:
|
||||
sarif_result = {
|
||||
"ruleId": finding.get("metadata", {}).get("detector", "unknown"),
|
||||
"level": _severity_to_sarif_level(finding.get("severity", "warning")),
|
||||
"message": {
|
||||
"text": finding.get("title", "Secret detected")
|
||||
},
|
||||
"locations": []
|
||||
}
|
||||
|
||||
# Add description if present
|
||||
if finding.get("description"):
|
||||
sarif_result["message"]["markdown"] = finding["description"]
|
||||
|
||||
# Add location if file path is present
|
||||
if finding.get("file_path"):
|
||||
location = {
|
||||
"physicalLocation": {
|
||||
"artifactLocation": {
|
||||
"uri": finding["file_path"]
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# Add region if line number is present
|
||||
if finding.get("line_start"):
|
||||
location["physicalLocation"]["region"] = {
|
||||
"startLine": finding["line_start"]
|
||||
}
|
||||
|
||||
sarif_result["locations"].append(location)
|
||||
|
||||
sarif_report["runs"][0]["results"].append(sarif_result)
|
||||
|
||||
activity.logger.info(f"Generated SARIF report with {len(sarif_report['runs'][0]['results'])} results")
|
||||
|
||||
return sarif_report
|
||||
|
||||
|
||||
def _severity_to_sarif_level(severity: str) -> str:
|
||||
"""Convert severity to SARIF level"""
|
||||
severity_map = {
|
||||
"critical": "error",
|
||||
"high": "error",
|
||||
"medium": "warning",
|
||||
"low": "note",
|
||||
"info": "note"
|
||||
}
|
||||
return severity_map.get(severity.lower(), "warning")
|
||||
@@ -0,0 +1,34 @@
|
||||
name: trufflehog_detection
|
||||
version: "1.0.0"
|
||||
vertical: secrets
|
||||
description: "Detect secrets with verification using TruffleHog"
|
||||
author: "FuzzForge Team"
|
||||
tags:
|
||||
- "secrets"
|
||||
- "trufflehog"
|
||||
- "verification"
|
||||
|
||||
workspace_isolation: "shared"
|
||||
|
||||
parameters:
|
||||
type: object
|
||||
properties:
|
||||
verify:
|
||||
type: boolean
|
||||
default: true
|
||||
description: "Verify discovered secrets"
|
||||
|
||||
max_depth:
|
||||
type: integer
|
||||
default: 10
|
||||
description: "Maximum directory depth to scan"
|
||||
|
||||
default_parameters:
|
||||
verify: true
|
||||
max_depth: 10
|
||||
|
||||
required_modules:
|
||||
- "trufflehog"
|
||||
|
||||
supported_volume_modes:
|
||||
- "ro"
|
||||
@@ -0,0 +1,104 @@
|
||||
"""TruffleHog Detection Workflow"""
|
||||
|
||||
from datetime import timedelta
|
||||
from typing import Dict, Any
|
||||
from temporalio import workflow
|
||||
from temporalio.common import RetryPolicy
|
||||
|
||||
@workflow.defn
|
||||
class TrufflehogDetectionWorkflow:
|
||||
"""Scan code for secrets using TruffleHog."""
|
||||
|
||||
@workflow.run
|
||||
async def run(self, target_id: str, verify: bool = False, concurrency: int = 10) -> Dict[str, Any]:
|
||||
workflow_id = workflow.info().workflow_id
|
||||
run_id = workflow.info().run_id
|
||||
|
||||
workflow.logger.info(
|
||||
f"Starting TrufflehogDetectionWorkflow "
|
||||
f"(workflow_id={workflow_id}, target_id={target_id}, verify={verify})"
|
||||
)
|
||||
|
||||
results = {"workflow_id": workflow_id, "status": "running", "findings": []}
|
||||
|
||||
try:
|
||||
# Step 1: Download target
|
||||
workflow.logger.info("Step 1: Downloading target from MinIO")
|
||||
target_path = await workflow.execute_activity(
|
||||
"get_target", args=[target_id, run_id, "shared"],
|
||||
start_to_close_timeout=timedelta(minutes=5),
|
||||
retry_policy=RetryPolicy(
|
||||
initial_interval=timedelta(seconds=1),
|
||||
maximum_interval=timedelta(seconds=30),
|
||||
maximum_attempts=3
|
||||
)
|
||||
)
|
||||
workflow.logger.info(f"✓ Target downloaded to: {target_path}")
|
||||
|
||||
# Step 2: Scan with TruffleHog
|
||||
workflow.logger.info("Step 2: Scanning with TruffleHog")
|
||||
scan_results = await workflow.execute_activity(
|
||||
"scan_with_trufflehog",
|
||||
args=[target_path, {"verify": verify, "concurrency": concurrency}],
|
||||
start_to_close_timeout=timedelta(minutes=15),
|
||||
retry_policy=RetryPolicy(
|
||||
initial_interval=timedelta(seconds=2),
|
||||
maximum_interval=timedelta(seconds=60),
|
||||
maximum_attempts=2
|
||||
)
|
||||
)
|
||||
workflow.logger.info(
|
||||
f"✓ TruffleHog scan completed: "
|
||||
f"{scan_results.get('summary', {}).get('total_secrets', 0)} secrets found"
|
||||
)
|
||||
|
||||
# Step 3: Generate SARIF report
|
||||
workflow.logger.info("Step 3: Generating SARIF report")
|
||||
sarif_report = await workflow.execute_activity(
|
||||
"trufflehog_generate_sarif",
|
||||
args=[scan_results.get("findings", []), {"tool_name": "trufflehog", "tool_version": "3.63.2"}],
|
||||
start_to_close_timeout=timedelta(minutes=2)
|
||||
)
|
||||
|
||||
# Step 4: Upload results to MinIO
|
||||
workflow.logger.info("Step 4: Uploading results")
|
||||
try:
|
||||
results_url = await workflow.execute_activity(
|
||||
"upload_results",
|
||||
args=[workflow_id, scan_results, "json"],
|
||||
start_to_close_timeout=timedelta(minutes=2)
|
||||
)
|
||||
results["results_url"] = results_url
|
||||
workflow.logger.info(f"✓ Results uploaded to: {results_url}")
|
||||
except Exception as e:
|
||||
workflow.logger.warning(f"Failed to upload results: {e}")
|
||||
results["results_url"] = None
|
||||
|
||||
# Step 5: Cleanup
|
||||
workflow.logger.info("Step 5: Cleaning up cache")
|
||||
try:
|
||||
await workflow.execute_activity(
|
||||
"cleanup_cache", args=[target_path, "shared"],
|
||||
start_to_close_timeout=timedelta(minutes=1)
|
||||
)
|
||||
workflow.logger.info("✓ Cache cleaned up")
|
||||
except Exception as e:
|
||||
workflow.logger.warning(f"Cache cleanup failed: {e}")
|
||||
|
||||
# Mark workflow as successful
|
||||
results["status"] = "success"
|
||||
results["findings"] = scan_results.get("findings", [])
|
||||
results["summary"] = scan_results.get("summary", {})
|
||||
results["sarif"] = sarif_report or {}
|
||||
workflow.logger.info(
|
||||
f"✓ Workflow completed successfully: {workflow_id} "
|
||||
f"({results['summary'].get('total_secrets', 0)} secrets found)"
|
||||
)
|
||||
|
||||
return results
|
||||
|
||||
except Exception as e:
|
||||
workflow.logger.error(f"Workflow failed: {e}")
|
||||
results["status"] = "error"
|
||||
results["error"] = str(e)
|
||||
raise
|
||||
Reference in New Issue
Block a user