Access Review Triage
GRCEngClub/claude-grc-engineering
Helps you triage a quarterly user access review from an Okta, Azure AD, AWS IAM, GitHub, or generic CSV/JSON export.
Agent skill
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…
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-soc2-type2-audit-preparation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-soc2-type2-audit-preparation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/performing-soc2-type2-audit-preparation .claude/skills/performing-soc2-type2-audit-preparation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "performing-soc2-type2-audit-preparation" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-soc2-type2-audit-preparation into .claude/skills/performing-soc2-type2-audit-preparation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-soc2-type2-audit-preparation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-soc2-type2-audit-preparationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-soc2-type2-audit-preparation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-soc2-type2-audit-preparation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/performing-soc2-type2-audit-preparation .agents/skills/performing-soc2-type2-audit-preparation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "performing-soc2-type2-audit-preparation" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-soc2-type2-audit-preparation into .agents/skills/performing-soc2-type2-audit-preparation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-soc2-type2-audit-preparation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-soc2-type2-audit-preparation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-soc2-type2-audit-preparation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/performing-soc2-type2-audit-preparation .cursor/skills/performing-soc2-type2-audit-preparation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "performing-soc2-type2-audit-preparation" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-soc2-type2-audit-preparation into .cursor/skills/performing-soc2-type2-audit-preparation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-soc2-type2-audit-preparation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/performing-soc2-type2-audit-preparation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-soc2-type2-audit-preparation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-soc2-type2-audit-preparation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/performing-soc2-type2-audit-preparation .gemini/skills/performing-soc2-type2-audit-preparation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "performing-soc2-type2-audit-preparation" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-soc2-type2-audit-preparation into .gemini/skills/performing-soc2-type2-audit-preparation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-soc2-type2-audit-preparation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-soc2-type2-audit-preparationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-soc2-type2-audit-preparation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/performing-soc2-type2-audit-preparation .github/skills/performing-soc2-type2-audit-preparation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "performing-soc2-type2-audit-preparation" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-soc2-type2-audit-preparation into .github/skills/performing-soc2-type2-audit-preparation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-soc2-type2-audit-preparation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-soc2-type2-audit-preparation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mukul975/Anthropic-Cybersecurity-Skills performing-soc2-type2-audit-preparation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/performing-soc2-type2-audit-preparation .opencode/skills/performing-soc2-type2-audit-preparation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "performing-soc2-type2-audit-preparation" agent skill from https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/main/skills/performing-soc2-type2-audit-preparation into .opencode/skills/performing-soc2-type2-audit-preparation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performing-soc2-type2-audit-preparation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
performing-soc2-type2-audit-preparationAutomates 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…
Performing Soc2 Type2 Audit Preparation is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. 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.
Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts, reference files and assets (for example `assets/template.md`, `references/api-reference.md` and `references/standards.md`).
It sits in Legal & Compliance, covering SOC 2 and security compliance, Audit readiness and Digital forensics. It works with Amazon Web Services, Google Cloud, Microsoft Azure and GitHub. The repository describes itself as: 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io…. The licence is Apache-2.0.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 54a7988. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 2 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.github.compagerduty.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Performing Soc2 Type2 Audit Preparation loads about 2.7k tokens when it runs, and up to ~7.3k if it reads all its reference files. Until then it costs about 139 tokens; SKILL.md has 420 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from mukul975/Anthropic-Cybersecurity-Skills at commit 54a7988, republished under its Apache-2.0 licence (© mukul975). 420 words, ~2,651 tokens.
.claude/skills/performing-soc2-type2-audit-preparation/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.boto3, requests, pyyaml dependenciesSOC 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 |
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.
CC3 - Risk Assessment: Risk identification, fraud risk analysis, change impact assessment, risk tolerance definition.
CC4 - Monitoring Activities: Ongoing control evaluations, deficiency identification, remediation tracking, internal audit.
CC5 - Control Activities: Policy-to-procedure mapping, technology controls, deployment of controls across the entity.
CC6 - Logical and Physical Access Controls: Authentication, authorization, access provisioning/deprovisioning, physical security, encryption.
CC7 - System Operations: Anomaly detection, incident response, vulnerability management, change detection, event monitoring.
CC8 - Change Management: Change authorization, testing, approval workflows, emergency changes, rollback procedures.
CC9 - Risk Mitigation: Vendor risk management, business continuity, insurance, residual risk acceptance.
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",
},
},
}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),
})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:
if not 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 if not c["approved"]]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"])
if not result["passing"]:
send_alert(
channel="#compliance",
message=f"Control drift: {check['control']} - {check['check']}",
details=result["findings"],
)Organize collected evidence into structured packages per criteria:
evidence_package = {
"audit_period": {"start": "2025-04-01", "end": "2026-03-31"},
"criteria_packages": {
"CC1_Control_Environment": {
"CC1.1": ["signed_acknowledgments.csv"],
"CC1.2": ["board_minutes_q1.pdf", "board_minutes_q2.pdf"],
},
"CC6_Logical_Physical_Access": {
"CC6.1": ["okta_mfa_policy.json", "iam_users_mfa_status.csv"],
"CC6.2": ["access_review_q1.csv", "access_review_q2.csv"],
"CC6.3": ["offboarding_tickets.csv", "terminated_user_audit.csv"],
},
"CC7_System_Operations": {
"CC7.1": ["cloudtrail_config.json", "siem_dashboard.png"],
"CC7.2": ["guardduty_findings_summary.csv"],
"CC7.3": ["vulnerability_scan_reports/"],
},
"CC8_Change_Management": {
"CC8.1": ["merged_prs_with_approvals.csv"],
},
},
}import boto3
from datetime import datetime, timedelta
iam = boto3.client("iam")
# Find users with no activity in 90 days
inactive_threshold = datetime.utcnow() - timedelta(days=90)
report = iam.get_credential_report()["Content"].decode()
inactive_users = []
for line in report.strip().split("\n")[1:]:
fields = line.split(",")
username = fields[0]
last_used = fields[4]
if last_used not in ("N/A", "no_information"):
last_date = datetime.strptime(last_used, "%Y-%m-%dT%H:%M:%S+00:00")
if last_date < inactive_threshold:
inactive_users.append({"user": username, "last_active": last_used})import requests
headers = {"Authorization": f"Bearer {scanner_token}"}
scans = requests.get(
"https://scanner.example.com/api/v1/scans",
params={"status": "completed", "since": "2025-04-01"},
headers=headers,
).json()
vuln_evidence = {"scan_count": len(scans), "critical_findings": 0, "high_findings": 0}
for scan in scans:
findings = requests.get(
f"https://scanner.example.com/api/v1/scans/{scan['id']}/findings",
headers=headers,
).json()
vuln_evidence["critical_findings"] += len([f for f in findings if f["severity"] == "critical"])
vuln_evidence["high_findings"] += len([f for f in findings if f["severity"] == "high"])incidents = requests.get(
"https://pagerduty.com/api/v1/incidents",
params={"since": "2025-04-01", "until": "2026-03-31"},
headers={"Authorization": f"Token token={pd_token}"},
).json()
ir_evidence = {
"total_incidents": len(incidents["incidents"]),
"incidents": [
{
"id": inc["id"],
"title": inc["title"],
"severity": inc["urgency"],
"created": inc["created_at"],
"resolved": inc.get("last_status_change_at"),
}
for inc in incidents["incidents"]
],
}© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 7 other files (scripts, references, assets) in skills/performing-soc2-type2-audit-preparation of mukul975/Anthropic-Cybersecurity-Skills.
Open the folder on GitHubat commit 54a7988
Performing Soc2 Type2 Audit Preparation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Performing Soc2 Type2 Audit Preparation this skillmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Access Review TriageGRCEngClub/claude-grc-engineering | 419 | — | ~2.4k | Automated safety check: Notes | Custom licence | |
| Provider Bug Reviewmondoohq/mql | 412 | — | ~2.9k | Automated safety check: Pass | Custom licence | |
| Update Provider Depsmondoohq/mql | 412 | — | ~4.5k | Automated safety check: Pass | Custom licence | |
| Trust Center BuilderGRCEngClub/claude-grc-engineering | 419 | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| Provider API Call Dedupmondoohq/mql | 412 | — | ~7.7k | Automated safety check: Pass | Custom licence |
GRCEngClub/claude-grc-engineering
Helps you triage a quarterly user access review from an Okta, Azure AD, AWS IAM, GitHub, or generic CSV/JSON export.
mondoohq/mql
Deep static code review of an mql provider for logic errors, nil-handling bugs, pagination truncation, caching/id collisions, and other defects that silently give users wrong data.
mondoohq/mql
Upgrade an mql provider's vendored SDKs (all providers or a named subset), audit the new versions for breaking changes and fix call sites while keeping shipped MQL fields backwards-compatible, check…
GRCEngClub/claude-grc-engineering
Builds and deploys a serverless trust center that publishes a company's compliance posture, with gated access to audit reports and an admin dashboard.
mondoohq/mql
A skill your agent uses when a provider scan is slow, times out, or trips rate limits (429, throttling, Retry-After), when the same request URL appears many times in a debug log, when an asset's…
briiirussell/cybersecurity-skills
Audit, design, and migrate Identity and Access Management — cloud provider IAM (AWS, GCP, Azure), identity providers (Okta, Entra ID / Azure AD, Auth0, Google Workspace), application authorization…
mukul975/Anthropic-Cybersecurity-Skills
Weighs infrastructure, TTP, malware code and timing evidence with the Diamond Model and competing hypotheses to reach a confidence-rated attribution.
mukul975/Anthropic-Cybersecurity-Skills
Walks through reverse engineering Go-compiled malware in Ghidra: parsing buildinfo and pclntab, recovering stripped function names and extracting dependencies.
mukul975/Anthropic-Cybersecurity-Skills
Guides forensic analysis of Windows LNK shortcut files and Jump Lists with LECmd, JLECmd and manual parsing to show file access and program execution.
mukul975/Anthropic-Cybersecurity-Skills
Hunts Windows malware persistence with Sysinternals Autoruns, covering run keys, services, scheduled tasks and drivers, with baseline comparison.
mukul975/Anthropic-Cybersecurity-Skills
Guides a Windows forensic examination of the NTFS Master File Table to recover deleted-file evidence, build timelines and spot timestomping.
mukul975/Anthropic-Cybersecurity-Skills
Detects DNS tunneling, ICMP exfiltration and HTTP-based covert channels in packet captures and DNS logs when hunting for hidden command-and-control traffic.
Categories
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…. Performing Soc2 Type2 Audit Preparation is an agent skill from mukul975/Anthropic-Cybersecurity-Skills. 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.
Performing Soc2 Type2 Audit Preparation fits situations like: maintaining SOC 2 Type II certification; tasks that involve SOC 2 and security compliance; tasks that involve Audit readiness.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-soc2-type2-audit-preparation -a claude-code`. Or copy the skill folder (skills/performing-soc2-type2-audit-preparation in mukul975/Anthropic-Cybersecurity-Skills) into .claude/skills/performing-soc2-type2-audit-preparation in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-soc2-type2-audit-preparation -a codex`. Or copy the skill folder (skills/performing-soc2-type2-audit-preparation in mukul975/Anthropic-Cybersecurity-Skills) into .agents/skills/performing-soc2-type2-audit-preparation in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill performing-soc2-type2-audit-preparation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/performing-soc2-type2-audit-preparation, .gemini/skills/performing-soc2-type2-audit-preparation, .github/skills/performing-soc2-type2-audit-preparation and .opencode/skills/performing-soc2-type2-audit-preparation in your project.
Going by SKILL.md and its folder, Performing Soc2 Type2 Audit Preparation needs Python for the scripts in its folder. Our summary lists: Python 3.
SKILL.md names 2 domains. In commands or code: api.github.com and pagerduty.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Performing Soc2 Type2 Audit Preparation is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Performing Soc2 Type2 Audit Preparation: Access Review Triage (GRCEngClub/claude-grc-engineering, 419 stars), Provider Bug Review (mondoohq/mql, 412 stars), Update Provider Deps (mondoohq/mql, 412 stars) and Trust Center Builder (GRCEngClub/claude-grc-engineering, 419 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mukul975 (a GitHub user) maintains it in mukul975/Anthropic-Cybersecurity-Skills, which has 34,116 GitHub stars. The repository holds 644 skills in this directory. The repository was last updated on August 31, 2026.
Source: mukul975/Anthropic-Cybersecurity-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.