Automates SOC 2 Type II audit preparation including gap assessment against AICPA Trust Services Criteria (CC1-CC9), evidence collection from cloud providers and identity systems, control testing validation, remediation tracking, and continuous compliance monitoring. Covers all five TSC categories (Security, Availability, Processing Integrity, Confidentiality, Privacy) with automated evidence gathering from AWS, Azure, GCP, Okta, GitHub, and Jira. Use when preparing for or maintaining SOC 2 Type II certification.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
Automates SOC 2 Type II audit preparation including gap assessment against AICPA Trust Services Criteria (CC1-CC9), evidence collection from cloud providers and identity systems, control testing validation, remediation tracking, and continuous compliance monitoring. Covers all five TSC categories (Security, Availability, Processing Integrity, Confidentiality, Privacy) with automated evidence gathering from AWS, Azure, GCP, Okta, GitHub, and Jira. Use when preparing for or maintaining SOC 2 Type II certification.
When preparing for a SOC 2 Type II audit engagement with a CPA firm
When conducting a gap assessment against AICPA Trust Services Criteria
When automating evidence collection across cloud infrastructure and identity providers
When validating that controls have operated effectively over the audit period (3-12 months)
When building continuous compliance monitoring to maintain SOC 2 posture between audits
When remediating control gaps identified during readiness assessment
Prerequisites
Familiarity with AICPA Trust Services Criteria (CC1-CC9)
Access to cloud provider APIs (AWS, Azure, or GCP) with read-only permissions
Access to identity provider (Okta, Azure AD, Google Workspace)
Access to version control system (GitHub, GitLab)
Access to ticketing system (Jira, Linear, ServiceNow)
Python 3.8+ with boto3, requests, pyyaml dependencies
Appropriate authorization to collect compliance evidence
Instructions
1. Understand the Trust Services Criteria
SOC 2 is built on five Trust Services Categories defined by AICPA. Security (Common Criteria CC1-CC9) is mandatory; the others are selected based on business relevance:
Category
Criteria
Focus
Security (mandatory)
CC1-CC9
Control environment, risk, access, operations, change management
Availability
A1
System uptime and disaster recovery
Processing Integrity
PI1
Accurate and complete data processing
Confidentiality
C1
Protection of confidential information
Privacy
P1-P8
Personal information lifecycle
2. Common Criteria Breakdown (CC1-CC9)
CC1 - Control Environment: Board oversight, management structure, integrity and ethical values, HR policies, accountability.
CC2 - Communication and Information: Internal/external communication of security policies, system boundaries, roles, and responsibilities.
Before the audit period begins, perform a readiness assessment 8-12 weeks in advance:
# Define control matrix against CC criteria
gap_assessment = {
"CC1": {
"CC1.1": {
"criteria": "COSO Principle 1: Demonstrates commitment to integrity",
"control": "Code of conduct signed annually by all employees",
"evidence": "Signed acknowledgments in HR system",
"status": "implemented",
"gap": None,
},
"CC1.2": {
"criteria": "COSO Principle 2: Board exercises oversight",
"control": "Quarterly board security reviews",
"evidence": "Board meeting minutes with security agenda items",
"status": "partial",
"gap": "No documented security committee charter",
},
},
}
4. Automate Evidence Collection
Collect evidence continuously throughout the audit period from integrated systems:
import boto3
# CC6 Evidence: AWS IAM access controls
iam = boto3.client("iam")
# Collect MFA status for all IAM users
users = iam.list_users()["Users"]
mfa_evidence = []
for user in users:
mfa_devices = iam.list_mfa_devices(UserName=user["UserName"])
mfa_evidence.append({
"user": user["UserName"],
"mfa_enabled": len(mfa_devices["MFADevices"]) > 0,
"created": user["CreateDate"].isoformat(),
})
# CC7 Evidence: AWS CloudTrail logging status
cloudtrail = boto3.client("cloudtrail")
trails = cloudtrail.describe_trails()["trailList"]
logging_evidence = []
for trail in trails:
status = cloudtrail.get_trail_status(Name=trail["TrailARN"])
logging_evidence.append({
"trail": trail["Name"],
"is_logging": status["IsLogging"],
"multi_region": trail.get("IsMultiRegionTrail", False),
"log_validation": trail.get("LogFileValidationEnabled", False),
})
5. Validate Control Effectiveness
For Type II audits, demonstrate controls operated effectively over the entire audit period:
import requests
# CC8 Evidence: Change management - verify all production changes# had tickets, approvals, and testing before deployment
headers = {"Authorization": f"token {github_token}"}
prs = requests.get(
"https://api.github.com/repos/org/repo/pulls",
params={"state": "closed", "base": "main", "per_page": 100},
headers=headers,
).json()
change_evidence = []
for pr in prs:
ifnot pr.get("merged_at"):
continue
reviews = requests.get(pr["url"] + "/reviews", headers=headers).json()
approved = any(r["state"] == "APPROVED"for r in reviews)
change_evidence.append({
"pr_number": pr["number"],
"title": pr["title"],
"merged_at": pr["merged_at"],
"approved": approved,
})
# Flag PRs merged without approval (control exception)
exceptions = [c for c in change_evidence ifnot c["approved"]]
6. Continuous Compliance Monitoring
Set up automated checks that run daily to detect control drift:
# Daily compliance check - run via cron or Lambda
checks = [
{"control": "CC6.1", "check": "All IAM users have MFA enabled"},
{"control": "CC6.6", "check": "No public S3 buckets"},
{"control": "CC7.1", "check": "CloudTrail logging enabled"},
{"control": "CC7.2", "check": "GuardDuty findings under threshold"},
{"control": "CC8.1", "check": "All PRs have required reviews"},
]
for check in checks:
result = run_compliance_check(check["control"])
ifnot result["passing"]:
send_alert(
channel="#compliance",
message=f"Control drift: {check['control']} - {check['check']}",
details=result["findings"],
)
7. Prepare Evidence Packages for Auditors
Organize collected evidence into structured packages per criteria:
