Atlas / Skills / sushegaad / Claude-Skills-Governance-Risk-and-Compliance

Claude-Skills-Governance-Risk-and-ComplianceBLOCK

skills/sushegaad/claude-skills-governance-risk-and-compliance

Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP, GDPR, HIPAA, NIST CSF, PCI DSS, EU AI Act, ISO 42001, ISO 27701, DORA, CSRD, India's DPDPA, CMMC 2.0, NIST AI Risk, SWIFT, CCPA/CPRA, and others. Benchmark 89% (with skills) vs 55%

Verdict
BLOCK
Grade
D
Trust score
60 /100
Version
—
Hosts
4 documented
License
MIT
Stars
950
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP, GDPR, HIPAA, NIST CSF, PCI DSS, TSA Cybersecurity, ISO 42001 AI Management System, ISO 27701 Privacy Information Management, DORA Digital Operational Resilience, India's Digital Personal Data Protection Act (DPDPA), CMMC 2.0 Cybersecurity Maturity Model Certification, NIST AI Risk Management Framework, SWIFT Customer Security Programme (CSP), Australian Information Security Manual (ISM), EU NIS2 Directive, CCPA/CPRA California Privacy, ITAR (International Traffic in Arms Regulations), Brazil's LGPD (Lei Geral de Proteção de Dados), EU CSRD (Corporate Sustainability Reporting Directive), CIS Controls v8 (CIS Top 18), EAR (Export Administration Regulations), NIST SP 800-53 (Security and Privacy Controls for Federal Systems), EU AI Act (Regulation (EU) 2024/1689), Section 508 (US Federal ICT Accessibility), WCAG (Web Content Accessibility Guidelines), NZISM (New Zealand Information Security Manual), Vietnam PDPL (Law on Personal Data Protection No. 91/2025/QH15), EU CRA (Cyber Resilience Act, Regulation (EU) 2024/2847), Saudi Arabia GRC (NCA ECC, Saudi PDPL, SAMA, CST), UAE GRC (Federal PDPL, DIFC, ADGM, CBUAE, ICT Health Law), TISAX (VDA ISA / ENX automotive supplier security), TPRM (third-party/vendor risk), UK Cyber Essentials, and SOX ITGC — powered by Claude Skills. Updated Monthly.

Benchmarked across 180 test cases using the eval framework — each graded against at least 5 verifiable assertions by independent agents (902 assertions in total). Skills scored 89% vs a baseline of 55%.

[](../../releases/tag/v2.1.0) [](LICENSE) [](#the-skills) [](https:/

Read from source at commit 7a840ef8562cOBSERVED · 2026-10-12
Advertisement
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
claude-desktopmentioned
copilotmentioned
cursormentioned
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: ccpa
description: >
  California Consumer Privacy Act (CCPA) and California Privacy Rights Act (CPRA)
  compliance advisor — business threshold analysis, consumer rights fulfillment
  (access, delete, correct, opt-out of sale/sharing, limit SPI, ADMT opt-out),
  privacy notice drafting, service provider vs. contractor vs. third-party
  classification, sensitive personal information (SPI) handling, data minimization,
  opt-out mechanisms (including GPC), cybersecurity audits and risk assessments
  (live since Jan 1, 2026), ADMT obligations (effective 2026, deadline Jan 1, 2027),
  CPPA enforcement (Disney $2.75M, PlayOn $1.1M, Ford $375K), penalty exposure,
  GDPR comparison, and gap assessments for businesses operating in or targeting
  California residents.
---

# CCPA/CPRA Compliance Advisor

> **Last verified:** 2026-10-03

You are an expert on California's comprehensive privacy laws:
- **CCPA**: California Consumer Privacy Act (Cal. Civ. Code §1798.100 et seq.), effective January 1, 2020
- **CPRA**: California Privacy Rights Act (Proposition 24), effective January 1, 2023 — significantly amends and expands CCPA, creates the California Privacy Protection Agency (CPPA)

## Applicability Workflow

Work through these steps in order for any organization asking "does CCPA/CPRA apply to us?"

1. **Confirm entity type.** Must be a **for-profit business** doing business in California. Non-profits and government entities are generally not covered, though some CPRA provisions may apply indirectly through service provider/contractor obligations flowing down from a covered business.
2. **Test the three thresholds** — the business is covered if it meets **at least one**:

| # | Threshold | Exact Figure |
|---|---|---|
| 1 | Annual gross revenue | Exceeds **$25 million** in the preceding calendar year |
| 2 | Data volume | Annually buys, sells, receives, or shares the personal information of **100,000 or more** consumers or households |
| 3 | Revenue from data monetization | Derives **50% or more** of annual revenue from selling or sharing consumers' personal information |

3. **Classify each downstream data recipient.** Applicability findings are incomplete without classifying who the business shares PI with:

| Classification | Definition | Sale? |
|---|---|---|
| **Service Provider** | Processes PI on behalf of the business under a written contract that prohibits further use beyond the specified business purpose | Not a sale |
| **Contractor** *(CPRA addition)* | Receives PI under a contract that prohibits use for any purpose other than specified; must certify compliance | Not a sale |
| **Third Party** | Receives PI but is not a service provider or contractor | May constitute a sale or sharing |

4. **Document the determination** — revenue and data-volume thresholds must be reassessed annually; vendor classifications should be reassessed whenever a contract is renewed or a new data recipient is onboarded.

## Key Definitions

- **Personal Information (PI)**: Information that identifies, relates to, describes, or could reasonably be linked to a consumer or household. Includes name, email, IP address, browsing history, purchase history, biometric data, geolocation.
- **Sensitive Personal Information (SPI)** *(CPRA addition)*: PI that reveals SSN/government ID, account credentials, precise geolocation, racial/ethnic origin, religious beliefs, union membership, genetic/biometric data, health/medical data, sexual orientation, or contents of consumer communications. See the full SPI category table and right-to-limit workflow below.
- **Sale**: Disclosing PI to a third party for monetary **or other valuable consideration** (broad definition — includes data brokering).
- **Sharing** *(CPRA addition)*: Disclosing PI to a third party for **cross-context behavioral advertising**, even without monetary consideration.
- **Service Provider**: Processes PI on behalf of a business under a written contract that prohibits further use; not considered a sale.
- **Contractor** *(CPRA addition)*: Entity receiving PI under a contract that prohibits use for any other purpose; must certify compliance.
- **Third Party**: Entity that receives PI from a business but is not a service provider or contractor.

## Consumer Rights

| Right | Description | Response Deadline |
|---|---|---|
| **Right to Know** (§1798.110 / §1798.115) | Access specific PI collected, categories, sources, purposes, third parties | 45 days (+ 45-day extension) |
| **Right to Delete** (§1798.105) | Delete PI collected from the consumer; exceptions apply | 45 days (+ 45-day extension) |
| **Right to Correct** (§1798.106) | Correct inaccurate PI *(CPRA addition)* | 45 days (+ 45-day extension) |
| **Right to Opt-Out of Sale/Sharing** (§1798.120) | Stop sale or sharing of PI to third parties | Immediate upon request; propagate within 15 business days |
| **Right to Limit SPI Use** (§1798.121) | Limit use/disclosure of SPI to what's necessary *(CPRA addition)* | 15 business days |
| **Right to Non-Discrimination** (§1798.125) | Cannot deny goods/services or charge different prices for exercising rights | N/A |
| **Right to Data Portability** | Receive PI in portable, usable format | Included in right to know |
| **Right to Opt-In (minors)** | Opt-in required for sale/sharing of minors' PI (under 16); parental consent under 13 | N/A |
| **Automated Decision-Making (ADMT)** (§1798.185(a)(16)) | Right to opt-out of ADMT; right to access logic; right to human review. **Regulations finalized and effective January 1, 2026. Compliance deadline for ADMT opt-out mechanism: January 1, 2027.** | Per CPPA regulations |

### General Request-Handling Principles

- **Response timeline (state it in every request-handling answer):** confirm receipt within **10 business days** with a description of the verification process (Regs §7021(a)); substantive response within **45 calendar days**, extendable once by a further **45 days** with notice to the consumer (§179
04

Trust audit

BLOCKgrade D · trust 60/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)FAIL
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (3 observation(s))
Shell
declared (2 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (25)

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
support.js:844
const fn = new Function(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
support.js:1218
new Function("React", "module", "exports", "require", code)(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHPrompt injection · prompt.override · CWE-94, CWE-1427
grc-workspace/rerun-2026-09/cyber-essentials-evals/eval-282/with_skill/response.txt:16
**Bottom line for your gap assessment:** your two biggest workstreams will be (1) confirming and enforcing MFA across every M365 and AWS account — this is your automatic-fail risk — and (2) making sur
Why it matters. asks the agent to drop prior instructions or safety
Fix. remove the instruction
MEDIUMInventory / provenance · inv.binary · CWE-1104
.DS_Store
.DS_Store
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
MEDIUMInventory / provenance · inv.binary · CWE-1104
CCPA - Claude Skill/ccpa.skill
ccpa.skill
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
MEDIUMInventory / provenance · inv.binary · CWE-1104
CIS Controls - Claude Skill/cis-controls.skill
cis-controls.skill
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
MEDIUMInventory / provenance · inv.binary · CWE-1104
CMMC - Claude Skill/cmmc.skill
cmmc.skill
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
MEDIUMInventory / provenance · inv.binary · CWE-1104
CSRD - Claude Skill/csrd.skill
csrd.skill
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
LOWInventory / provenance · inv.hidden_file · CWE-1104
.DS_Store
.DS_Store
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
assets/.DS_Store
.DS_Store
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
assets/Logos/.DS_Store
.DS_Store
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
grc-workspace/nist-800-53-evals/eval-119/without_skill/grading.json:13
"evidence": "Part B Section 1 states: 'Use of MD5, RC4, DES, 3DES, export-grade ciphers, and SSL 3.0 / TLS 1.0 / TLS 1.1 is explicitly prohibited and blocked at the infrastructure level.' Section 2 st
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements-dev.txt
pytest, PyYAML
Why it matters. 2 requirement(s) not pinned with ==
Fix. pin exact versions
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
README.md:80
<iframe src="https://www.youtube.com/embed/-IBLNR0N2vE" title="Claude Skills for GRC Demo" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-pictu
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
grc-workspace/rerun-2026-07/swift-csp-evals/eval-72/without_skill/outputs/response.md:9
- **The control's underlying objective is to protect against credential/session compromise on the endpoint used to access SWIFT infrastructure.** A software TOTP app installed on the same general-purp
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
grc-workspace/rerun-2026-07/swift-csp-evals/eval-72/without_skill/response.txt:9
- **The control's underlying objective is to protect against credential/session compromise on the endpoint used to access SWIFT infrastructure.** A software TOTP app installed on the same general-purp
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
index.html:233
<iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen="" src="https://www.youtube.com/embed/-IBLNR0N2vE" title="Claude Ski
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
plugins/tprm/skills/tprm/references/questionnaires-and-contracts.md:14
8. **Integration risk** — OAuth scopes requested, token storage/rotation, webhook security, least-privilege API design (post-Salesloft Drift, treat OAuth grants as Tier-1 questions for any integrated
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
INFOInventory / provenance · inv.oversize · CWE-1104
assets/projects/responsible-ai-evals.png
assets/projects/responsible-ai-evals.png
Why it matters. 1489986 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
grc-skills-eval-results.html
grc-skills-eval-results.html
Why it matters. 3257264 bytes not read
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
grc-workspace/iteration-1/cmmc/eval-3-ssp-drafting/with_skill/outputs/response.md:64
Privileged accounts (those with Azure AD directory roles or elevated permissions to CUI systems) are subject to additional controls beyond standard user MFA:
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
grc-workspace/iteration-1/cmmc/eval-4-poam/with_skill/outputs/response.md:107
| **Weakness Description** | Numerous user accounts hold administrative or elevated privileges beyond what is required for their job functions. Several standard users have local administrator rights o
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
grc-workspace/iteration-1/cmmc/eval-4-poam/with_skill/outputs/response.md:109
| **Remediation Steps** | 1. Conduct a full privilege audit across all in-scope systems (Active Directory, servers, applications, network devices). 2. Define privilege tiers: standard user, power user
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
grc-workspace/iteration-1/cmmc/eval-4-poam/without_skill/outputs/response.md:173
| **Remediation Actions** | 1. Conduct a full access rights review for all user and service accounts. 2. Document a role-based access control (RBAC) matrix defining permissions by job function. 3. Rev
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
grc-workspace/iteration-1/eval-108-cis-mfa-safeguards/without_skill/outputs/response.md:47
**Description:** Require MFA for all administrative access accounts, where supported, on all enterprise assets, whether managed on-site or through a third-party provider. Administrative accounts have

Gates applied: instruction_override, no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 7a840ef8562cfull audit observations/trust-audit/skill/sushegaad__claude-skills-governance-risk-and-compliance.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-127a840ef8562cBLOCKD60first audit
06

Questions

What does the Claude-Skills-Governance-Risk-and-Compliance skill do?

Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP, GDPR, HIPAA, NIST CSF, PCI DSS, EU AI Act, ISO 42001, ISO 27701, DORA, CSRD, India's DPDPA, CMMC 2.0, NIST AI Risk, SWIFT, CCPA/CPRA, and others. Benchmark 89% (with skills) vs 55%

Is Claude-Skills-Governance-Risk-and-Compliance safe to install?

No — not without reading the findings first. The audit graded it D (60/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on.

What can Claude-Skills-Governance-Risk-and-Compliance access on my machine?

The audit observed that it reaches the network and runs shell commands. Each of those is consistent with what it says it does. Secrets in the source: none found.

Which assistants does Claude-Skills-Governance-Risk-and-Compliance work with?

Its documentation mentions claude-code, claude-desktop, copilot and cursor. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (7a840ef8562c), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement