Add folder anatomy (scripts/agent.py + references/api-reference.md) for 648 cybersecurity skills

Complete skill folder anatomy across all cybersecurity skills:
- scripts/agent.py: 80-150 line Python agents using real libraries (impacket,
  boto3, azure-mgmt-*, kubernetes, pefile, yara, scapy, shodan, stix2, etc.)
- references/api-reference.md: real API documentation with method signatures
- LICENSE: MIT license for all skill folders
This commit is contained in:
mukul975
2026-03-10 21:02:12 +01:00
parent c74d52fa30
commit 27c6414ca5
1390 changed files with 106806 additions and 0 deletions
@@ -0,0 +1,21 @@
MIT License
Copyright (c) 2025 Anthropic Agent Skills Contributors
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
@@ -0,0 +1,61 @@
# API Reference: AWS Macie Data Classification Agent
## Dependencies
| Library | Version | Purpose |
|---------|---------|---------|
| boto3 | >=1.28 | AWS SDK for Macie2 sensitive data discovery |
## CLI Usage
```bash
python scripts/agent.py \
--profile security-audit \
--region us-east-1 \
--output-dir /reports/ \
--output macie_report.json
```
## Functions
### `get_macie_client(profile, region)`
Creates boto3 Macie2 client with optional named profile.
### `enable_macie(client) -> dict`
Calls `client.get_macie_session()` to check status, then `client.enable_macie()` if needed.
### `list_s3_buckets_summary(client) -> list`
Calls `client.describe_buckets()` to get bucket inventory with encryption, public access, and classifiable object counts.
### `create_classification_job(client, bucket_names, job_name) -> dict`
Calls `client.create_classification_job(jobType="ONE_TIME", s3JobDefinition={...})` for targeted sensitive data discovery.
### `get_finding_statistics(client) -> dict`
Calls `client.get_finding_statistics(groupBy=...)` for severity and type breakdowns.
### `list_findings(client, severity, max_results) -> list`
Calls `client.list_findings()` with severity criterion, then `client.get_findings(findingIds=[...])` for details.
### `generate_report(client) -> dict`
Orchestrates all functions and compiles summary with public bucket identification.
## boto3 Macie2 Methods Used
| Method | Purpose |
|--------|---------|
| `enable_macie(status)` | Enable Macie service |
| `describe_buckets(criteria)` | S3 bucket inventory |
| `create_classification_job(...)` | Start discovery job |
| `get_finding_statistics(groupBy)` | Finding aggregations |
| `list_findings(findingCriteria)` | Filter findings |
| `get_findings(findingIds)` | Detailed finding data |
## Output Schema
```json
{
"summary": {"total_buckets": 45, "public_buckets": 2, "high_findings": 12},
"bucket_inventory": [{"name": "my-bucket", "public_access": "NOT_PUBLIC"}],
"high_findings": [{"type": "SensitiveData:S3Object/Personal", "bucket": "data-lake"}]
}
```
@@ -0,0 +1,165 @@
#!/usr/bin/env python3
"""AWS Macie data classification agent using boto3 for S3 sensitive data discovery."""
import argparse
import json
import logging
import os
import sys
from datetime import datetime
from typing import Dict, List, Optional
try:
import boto3
from botocore.exceptions import ClientError
except ImportError:
sys.exit("boto3 required: pip install boto3")
logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
logger = logging.getLogger(__name__)
def get_macie_client(profile: str = "", region: str = "us-east-1"):
"""Create Macie2 client."""
session = boto3.Session(profile_name=profile) if profile else boto3.Session()
return session.client("macie2", region_name=region)
def enable_macie(client) -> dict:
"""Enable Macie in the account if not already enabled."""
try:
client.get_macie_session()
return {"status": "already_enabled"}
except ClientError:
try:
client.enable_macie(status="ENABLED")
return {"status": "enabled"}
except ClientError as exc:
return {"error": str(exc)}
def list_s3_buckets_summary(client) -> List[dict]:
"""Get Macie's summary of S3 bucket inventory."""
try:
resp = client.describe_buckets(criteria={}, maxResults=50)
buckets = []
for b in resp.get("buckets", []):
buckets.append({
"name": b.get("bucketName", ""),
"region": b.get("region", ""),
"classifiable_objects": b.get("classifiableObjectCount", 0),
"classifiable_size": b.get("classifiableSizeInBytes", 0),
"encryption": b.get("serverSideEncryption", {}).get("type", "NONE"),
"public_access": b.get("publicAccess", {}).get("effectivePermission", "NOT_PUBLIC"),
"shared_access": b.get("sharedAccess", "NOT_SHARED"),
})
return buckets
except ClientError as exc:
logger.error("describe_buckets failed: %s", exc)
return []
def create_classification_job(client, bucket_names: List[str], job_name: str) -> dict:
"""Create a one-time sensitive data discovery job for specified buckets."""
try:
resp = client.create_classification_job(
jobType="ONE_TIME",
name=job_name,
s3JobDefinition={
"bucketDefinitions": [{
"accountId": boto3.client("sts").get_caller_identity()["Account"],
"buckets": bucket_names,
}]
},
description=f"Scan {len(bucket_names)} buckets for sensitive data",
)
return {"job_id": resp["jobId"], "job_arn": resp["jobArn"]}
except ClientError as exc:
return {"error": str(exc)}
def get_finding_statistics(client) -> dict:
"""Get statistics on Macie findings by severity and type."""
try:
by_severity = client.get_finding_statistics(
groupBy="severity.description",
)
by_type = client.get_finding_statistics(
groupBy="type",
)
return {
"by_severity": by_severity.get("countsBySeverity", []),
"by_type": by_type.get("countsByGroup", []),
}
except ClientError as exc:
return {"error": str(exc)}
def list_findings(client, severity: str = "High", max_results: int = 50) -> List[dict]:
"""List recent Macie findings filtered by severity."""
try:
resp = client.list_findings(
findingCriteria={
"criterion": {
"severity.description": {"eq": [severity]}
}
},
maxResults=max_results,
)
finding_ids = resp.get("findingIds", [])
if not finding_ids:
return []
details = client.get_findings(findingIds=finding_ids[:20])
return [{
"id": f.get("id", ""),
"type": f.get("type", ""),
"severity": f.get("severity", {}).get("description", ""),
"title": f.get("title", ""),
"bucket": f.get("resourcesAffected", {}).get("s3Bucket", {}).get("name", ""),
"count": f.get("count", 0),
"created": f.get("createdAt", ""),
} for f in details.get("findings", [])]
except ClientError as exc:
return [{"error": str(exc)}]
def generate_report(client) -> dict:
"""Generate Macie data classification report."""
report = {"analysis_date": datetime.utcnow().isoformat()}
report["macie_status"] = enable_macie(client)
report["bucket_inventory"] = list_s3_buckets_summary(client)
report["finding_statistics"] = get_finding_statistics(client)
report["high_findings"] = list_findings(client, "High")
report["critical_findings"] = list_findings(client, "Critical")
public_buckets = [b for b in report["bucket_inventory"]
if b.get("public_access") != "NOT_PUBLIC"]
report["public_buckets"] = public_buckets
report["summary"] = {
"total_buckets": len(report["bucket_inventory"]),
"public_buckets": len(public_buckets),
"high_findings": len(report["high_findings"]),
"critical_findings": len(report["critical_findings"]),
}
return report
def main():
parser = argparse.ArgumentParser(description="AWS Macie Data Classification Agent")
parser.add_argument("--profile", default="", help="AWS CLI profile")
parser.add_argument("--region", default="us-east-1")
parser.add_argument("--output-dir", default=".")
parser.add_argument("--output", default="macie_report.json")
args = parser.parse_args()
os.makedirs(args.output_dir, exist_ok=True)
client = get_macie_client(args.profile, args.region)
report = generate_report(client)
out_path = os.path.join(args.output_dir, args.output)
with open(out_path, "w") as f:
json.dump(report, f, indent=2, default=str)
logger.info("Report saved to %s", out_path)
print(json.dumps(report["summary"], indent=2))
if __name__ == "__main__":
main()