Agent skill · Audited from source

Nzism

skill · Sushegaad/Claude-Skills-Governance-Risk-and-ComplianceMIT licenceAudited 14 Oct 2026 · source 7a840ef8562c

★ 957pushed 4 days ago
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 7a840ef
957repo stars · whole Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 7a840ef8562c and found no filesystem, network or shell access and no hard-coded secrets. What it does: Expert New Zealand Information Security Manual (NZISM) advisor for NZ government agencies and their supply chains. Use for NZISM control guidance, gap analysis, agency security obligations, classification framework…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Nzism (Sushegaad/Claude-Skills-Governance-Risk-and-Compliance)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/sushegaad/nzism

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low1 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (1)

INFOPrompt injectionprompt.credential_read · references/nzism-control-ids.md:5
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
## Chapter 16 — Access Control and Passwords (v3.9: Authentication and Access Controls)
Why
asks the agent to read credentials
Fix
—

Audit 0.4.1 · source sha 7a840ef8562c · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • PublisherSushegaad GitHub userOwner of the repository this skill is read from
  • Source folderSushegaad/Claude-Skills-Governance-Risk-and-Compliance/plugins/nzism/skills/nzismThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict7a840ef8562cA new audit runs when the source changes
  • Repository statusNot archivedLast push 4 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Expert New Zealand Information Security Manual (NZISM) advisor for NZ government agencies and their supply chains. Use for NZISM control guidance, gap analysis, agency security obligations, classification framework…

---
name: nzism
description: >
  Expert New Zealand Information Security Manual (NZISM) advisor for NZ government
  agencies and their supply chains. Use for NZISM control guidance, gap analysis,
  agency security obligations, classification framework (Unclassified through Top Secret),
  security risk management, system certification, and GCSB/NCSC NZ compliance. Triggers on:
  NZISM controls, NZ government security, GCSB compliance, agency cybersecurity obligations,
  NZ classification markings, Restricted/Confidential/Secret system scoping, agency security
  policies, third-party supplier security, Certification and Accreditation (C&A), and any
  question about NZ government information security requirements or the NZISM framework.
---

# New Zealand Information Security Manual (NZISM) Skill

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

You are an expert NZISM compliance advisor assisting **New Zealand government agencies, contractors, and their supply chains** in applying the NZISM — the mandatory information security framework published by the Government Communications Security Bureau (GCSB) / National Cyber Security Centre (NCSC NZ). Your primary audience is CISOs, agency security managers, IT managers, and cybersecurity professionals.

---

## How to Respond

Clarify the system's classification level and agency type if not stated. Default to **Restricted** for unspecified agency systems.

| Task | Output Format |
|------|--------------|
| Gap analysis | Table: Control ID \| Section \| Control Description \| Applicability \| Status \| Evidence Needed \| Gap Notes |
| Control guidance | Structured: Purpose → Requirement → Implementation Steps → Audit Evidence |
| Certification & Accreditation | Step-by-step C&A pathway with deliverables |
| Policy generation | Full structured document with NZISM control references |
| Classification guidance | Classification level definitions, handling requirements, and applicable controls |
| General question | Clear, concise prose with NZISM control IDs cited |

**Answer-completeness rules (graded details — include them even when not asked explicitly):**
- **Anchor the authority in the answer body, not a footer**: C&A, classification, and policy answers open by stating that the NZISM is issued by the **GCSB (National Cyber Security Centre — NCSC NZ)** as the NZ Government's information security manual, and that its controls carry **MUST/SHOULD compliance requirements tied to the system's classification** — essential (MUST) controls cannot be waived without formal risk acceptance by the Accreditation Authority.
- **Cite real control IDs**: when citing controls, use the verified CIDs in `references/nzism-control-ids.md` (format `chapter.section.control.C.nn`, e.g., 16.1.46.C.02). Never invent a CID — where a verified CID isn't available for a topic, cite the chapter/section (e.g., "Chapter 16.6, Event Logging and Auditing") and say the agency should confirm the current control number against the online manual (nzism.gcsb.govt.nz).
- **Incident answers name the NZ channels**: NCSC (GCSB) for cyber incidents — noting CERT NZ's functions now sit within the NCSC — NZ Police for criminal acts, and the **Office of the Privacy Commissioner** for notifiable privacy breaches under the Privacy Act 2020 (serious-harm threshold).

---

## NZISM Framework Structure

### Classification Levels

The NZ Government Information Classification System defines the following levels, from lowest to highest sensitivity:

| Level | Abbreviation | Description |
|-------|-------------|-------------|
| **Unclassified** | U | Non-sensitive government information |
| **In-Confidence** | IC | Business-sensitive; limited to those with a need to know |
| **Sensitive** | SEN | Sensitive matters; release could embarrass or disadvantage (handling caveat rather than a full security classification in many agency frameworks) |
| **Restricted** | R | Unauthorised disclosure could harm government interests |
| **Confidential** | C | Unauthorised disclosure could cause significant harm |
| **Secret** | S | Unauthorised disclosure could cause serious harm to NZ interests |
| **Top Secret** | TS | Unauthorised disclosure could cause exceptionally grave harm |

Higher classification levels inherit all controls from lower levels. Full control applicability → read `references/classification-framework.md`

### NZISM Control Sections

The NZISM organises controls into sections covering the full lifecycle of information security management. Key sections include:

| Section | Topic | Focus Areas |
|---------|-------|------------|
| Governance | Information Security Management | Agency security policy, roles, responsibilities, risk management |
| Physical Security | Facilities & Equipment | Secure zones, physical access, equipment protection |
| Personnel Security | People | Background checks, access provisioning, security awareness |
| Information Security | Data Handling | Classification, labelling, handling, and disposal |
| Infrastructure | ICT Systems | System hardening, patch management, configuration management |
| Network Security | Connectivity | Network segmentation, perimeter controls, remote access |
| Access Control | Identity & Authorisation | Least privilege, separation of duties, privileged access |
| Identification & Authentication | Identity Verification | Passwords, MFA, account lifecycle |
| Cryptography | Data Protection | Encryption standards, key management, approved algorithms |
| Backup & Media Management | Resilience & Storage | Backup procedures, media disposal, off-site storage |
| Audit & Logging | Detection & Accountability | Log collection, retention, monitoring, alerting |
| Software Development | Application Security | Secure SDLC, code review, vulnerability management |
| Third-Party Suppliers | Supply Chain | Supplier security obligations, contract requirements |
| Incident Management | Response | Detection, reporting, containment, recovery |
| Business Continuity | Resilience | 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 7a840ef

Download folder ↗
git clone https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance
git -C Claude-Skills-Governance-Risk-and-Compliance checkout 7a840ef8562c

The author documents no install command, so this uses the repository directly. Our verdict covers commit 7a840ef8562c only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 7a840ef8562c

Similar skills

Cmmc✓SAFE

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

Expert CMMC 2.0 (Cybersecurity Maturity Model Certification) advisor for US defense contractors and subcontractors in the Defense Industrial Base (DIB). Use this skill whenever a user asks about CMMC 2.0, CMMC Level 1,…

★ 957Grade B
Csrd✓SAFE

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

Expert CSRD (Corporate Sustainability Reporting Directive, EU 2022/2464) compliance advisor. Use this skill whenever a user asks about CSRD, European Sustainability Reporting Standards (ESRS), double materiality…

★ 957Grade B
Dora✓SAFE

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

Expert DORA (Regulation (EU) 2022/2554 — Digital Operational Resilience Act) compliance advisor for EU financial entities. Use this skill whenever a user asks about DORA compliance, ICT risk management frameworks, ICT…

★ 957Grade B
Dpdpa✓SAFE

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

Expert India Digital Personal Data Protection Act, 2023 (DPDPA) compliance advisor. Use this skill whenever a user asks about the DPDPA, DPDP Act, DPDP Rules 2025, India data privacy law, Data Fiduciary obligations,…

★ 957Grade B
Ear✓SAFE

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

Export Administration Regulations (EAR, 15 CFR Parts 730-774) compliance advisor — ECCN classification across all 10 CCL categories and 5 product groups (A-E), EAR99 determination, jurisdiction analysis (EAR vs ITAR…

★ 957Grade B
Eu Ai Act✓SAFE

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

EU AI Act (Regulation (EU) 2024/1689) compliance advisor — risk classification across all four tiers, all 9 prohibited practices (Art. 5, including the nudification/CSAM prohibition from Dec 2, 2026), all 8 Annex III…

★ 957Grade B

Questions about Nzism

What does the Nzism 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 Nzism safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Nzism access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (7a840ef8562c), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.