# Shield pack: 27 compliance specialists and 11 workflows

> Shield routes compliance questions to 27 framework specialists and 11 GDPR and AI Act workflows, and adds assurance cases, an AI register and review rules. Not legal advice.

Canonical: https://bmad-plus.rochetta.fr/docs/packs/shield/
Language: en
BMAD+ version: 0.23.1
Documentation reviewed: 2026-10-19
Author: Laurent Rochetta
License: MIT

BMAD+ documentation › [Packs](https://bmad-plus.rochetta.fr/docs/packs/) › Shield pack: 27 compliance specialists and 11 workflows

Shield turns BMAD+ into a governance, risk and compliance (GRC) assistant. One orchestrator reads your question, spots the framework or frameworks it concerns, and routes it to a specialist agent: 27 of them, each dedicated to one regulation or standard, in six categories. Eleven further workflows cover the recurring GDPR and EU AI Act documents (impact assessments, breach response, privacy notices, cookie policies, AI risk classification). On top of that, Shield ships three evidence tools backed by real CLI commands: an assurance case, an AI processing register and compliance review rules.

> **Warning · Not legal advice** Every Shield report carries an AI-generated marking and a not-legal-advice notice. The output may be incomplete or out of date and does not replace a lawyer, a data protection officer or a certified auditor. A qualified person must review it before any compliance decision, filing or attestation.

<a id="when-to-use"></a>
## When to use it

- You must show that a product meets a regulation or a standard (GDPR, SOC 2, ISO 27001, PCI DSS, HIPAA, NIS2, DORA, EU AI Act and others) and want a structured gap analysis rather than a blank page.
- You need a standard GDPR or AI Act document: DPIA, breach notification, legitimate-interest test, privacy notice, cookie policy, AI risk class.
- You want audit evidence that is checked by commands, not asserted: an assurance case tied to a commit.
- You want a code review that says which compliance controls a change touches.

<a id="installed"></a>
## What is installed

Shield is a packaged pack: everything sits in `.agents/skills/pack-shield/`. That folder holds the pack skill `SKILL.md`, the orchestrator `shield-orchestrator.md`, `categories/` (the 27 specialists and the 11 workflows), `references/` (79 regulatory reference files), `shared/` (cross-framework mapper, gap-analysis and audit-report templates, assurance-case and AI-register procedures with their templates) and `review-rules/` (the six compliance review rules and their index). `bmad-plus doctor` checks that `SKILL.md` and `review-rules/index.yaml` are present.

<a id="frameworks"></a>
### The frameworks, by category

**Six categories, 27 specialist agents**

| Category | Agents | Frameworks |
| --- | --- | --- |
| Data Privacy | 5 | GDPR, CCPA/CPRA, LGPD, DPDPA, ISO/IEC 27701 |
| Cybersecurity | 6 | ISO/IEC 27001, NIST CSF 2.0, NIST SP 800-53 Rev. 5, CIS Controls v8, NIS2, Australian ISM |
| Industry Compliance | 6 | SOC 2, PCI DSS v4.0.1, HIPAA, SWIFT CSP, DORA, FedRAMP |
| Defense & Export | 4 | CMMC 2.0, ITAR, EAR, TSA Security Directives |
| AI Governance | 3 | EU AI Act 2024/1689, ISO/IEC 42001, NIST AI RMF 1.0 |
| Accessibility & ESG | 3 | WCAG 2.2, Section 508, CSRD |

The pack has 27 specialist agents, one per framework. The registry’s list of compliance tags names all 27, and the pack list of the installer reads “GRC compliance (27 frameworks)”.

<a id="specialists"></a>
### The 27 specialist agents

**Specialist agents, their framework and what they help with**

| Agent | Framework | Jurisdiction | Helps with |
| --- | --- | --- | --- |
| `gdpr-agent` | GDPR | EU, EEA, UK | Code and system audit, document drafting, Q&A, data-flow and PII review, DPIA, breach response, LIA (7 workflows) |
| `ccpa-agent` | CCPA / CPRA | California | Who must comply, consumer rights, obligations, enforcement exposure |
| `lgpd-agent` | LGPD | Brazil | Scope, principles, the ten legal bases, data-subject rights, differences from GDPR |
| `dpdpa-agent` | DPDPA | India | Notice, data-principal rights, fiduciary duties, children’s data, cross-border transfers |
| `iso27701-agent` | ISO/IEC 27701 | International | Gap analysis, policies, control guidance, privacy risk assessment, statement of applicability |
| `iso27001-agent` | ISO/IEC 27001 | International | Gap analysis, policy and document generation, control guidance, risk assessment, mandatory documentation checklist |
| `nist-csf-agent` | NIST CSF 2.0 | United States | Gap assessment, profiles, roadmap, cross-framework mapping, policies |
| `nist-800-53-agent` | NIST SP 800-53 Rev. 5 | US federal | System categorisation, baselines, control families, tailoring, overlays, SSP narratives, assessment |
| `cis-controls-agent` | CIS Controls v8 | International | Implementation groups, the 18 controls, mappings to other frameworks, gap assessment |
| `nis2-agent` | NIS2 | EU | Entity classification, gap assessment, incident reporting, management-body duties, ISO 27001 alignment |
| `ism-agent` | Australian ISM | Australia | Gap analysis, system authorisation, IRAP preparation, security documentation, Essential Eight versus ISM |
| `soc2-agent` | SOC 2 Type I/II | United States | Readiness and gap assessment, policies, control documentation, audit evidence, vendor risk questionnaires |
| `pci-dss-agent` | PCI DSS v4.0.1 | International | Cardholder-data environment scoping, gap assessment, SAQ selection, control guidance, policies |
| `hipaa-agent` | HIPAA | US healthcare | Compliance review, templates and policies, technical safeguards, explanations |
| `swift-csp-agent` | SWIFT CSP | International banking | Architecture types, the control framework, annual assessment and attestation timeline, common findings |
| `dora-agent` | DORA | EU financial sector | In-scope entities, ICT risk-management framework (Articles 5 to 16) |
| `fedramp-agent` | FedRAMP | US federal cloud | Readiness and gap assessment, authorisation documentation, NIST 800-53 control mapping |
| `cmmc-agent` | CMMC 2.0 | US defense | Gap assessment, system security plan, SPRS score, POA&M, CUI scoping |
| `itar-agent` | ITAR | US arms export | ITAR versus EAR jurisdiction, registration, licensing, agreements, deemed exports, voluntary disclosure, technology control plan |
| `ear-agent` | EAR | US dual-use export | Jurisdiction, ECCN classification, license requirement, license exceptions, end-user controls |
| `tsa-agent` | TSA Security Directives | US transport | Directive coverage by sector, critical cyber systems, incident reporting, coordinator designation |
| `eu-ai-act-agent` | EU AI Act 2024/1689 | EU | Eight-step compliance workflow, response format, timeline, penalties |
| `iso42001-agent` | ISO/IEC 42001 | International | Gap assessment, AI system impact assessment, AI risk assessment, statement of applicability, certification pathway |
| `nist-ai-rmf-agent` | NIST AI RMF 1.0 | United States | Govern, map, measure and manage functions, trustworthiness, gap assessment, AI risk register |
| `wcag-agent` | WCAG 2.2 | International | The four principles, accessibility audit, accessibility statement, ARIA, contrast, legal mapping |
| `section508-agent` | Section 508 | US federal | Regulatory framework, ICT coverage, filling a VPAT, accessibility audit |
| `csrd-agent` | CSRD | EU | Scope and thresholds, double materiality assessment, ESRS architecture, disclosure requirements |

<a id="workflows"></a>
### The 11 GDPR and AI Act workflows

**Workflow agents and the document each produces**

| Workflow | Purpose |
| --- | --- |
| `dpia-sentinel` | Data protection impact assessment, Article 35, with AI-specific considerations; nine-section report |
| `breach-sentinel` | Breach response, Articles 33 and 34: severity classification, 72-hour authority notification, data-subject notice, lessons learned |
| `legitimate-interest` | Legitimate interest assessment, Article 6(1)(f): purpose, necessity and balancing test |
| `privacy-advisor` | Assessment of an overall GDPR programme and posture |
| `privacy-notice-gen` | Privacy notice with the mandatory elements of Articles 13 and 14 |
| `privacy-policy-gen` | Full privacy policy for a site or an app |
| `cookie-policy-gen` | Cookie policy under ePrivacy and GDPR, with CNIL guidance |
| `ai-act-classifier` | Risk class of an AI system: prohibited, high-risk (Annex III), limited, minimal |
| `ai-act-roles` | Provider, deployer or importer: which obligations fall on you |
| `ai-act-fria` | Fundamental rights impact assessment, Article 27 |
| `ai-act-incidents` | Serious incident reporting workflow, Article 73 |

<a id="evidence-tools"></a>
### Evidence tools backed by the CLI

**Three evidence capabilities**

| Tool | Commands | What it guarantees |
| --- | --- | --- |
| Security assurance case | `bmad-plus assurance init`, `run`, `verify` | A claim counts as supported only if the check behind it ran at the commit concerned, recorded in a hash-chained ledger. Missing, failed or stale evidence leaves the claim unsupported. |
| AI processing register | `bmad-plus ai-register init`, `check` | Compares `_bmad/ai-processing-register.yaml` with the AI integrations found in the project and warns about unregistered ones. Warnings never fail the command. |
| Compliance review rules | `bmad-plus review scope`, `review rules <path>` | Six path-scoped checklists tagged with controls such as `ISO27001:A.8.5`, `SOC2:CC6.1` or `GDPR:Art.32`, so a review lists the controls a change touches. |

The six review rules are `shield-access-control`, `shield-personal-data`, `shield-cryptography`, `shield-logging`, `shield-ai-integrations` and `shield-change-and-supply-chain`. They add to the built-in review rules and never replace them; a project can replace or disable them in `_bmad/review-rules.yaml`.

<a id="quick-start"></a>
## Quick start

1. **Install the pack** Core is added automatically. Shield needs only Node.js 20 for the installer; the evidence commands run from the same CLI.

   ```sh
   npx bmad-plus install --packs shield
   ```
2. **Ask the orchestrator** Name the framework if you know it, or describe your situation; Shield asks two or three clarifying questions (jurisdiction, industry, data types) when the framework is ambiguous.

   ```sh
   Shield, audit my app for GDPR compliance
   ```
3. **Check the install** The diagnostic confirms that the pack skill and the review rules index are present.

   ```sh
   npx bmad-plus doctor
   ```

<a id="examples"></a>
## Copyable examples

<a id="example-shield-gdpr-audit"></a>
### Audit a product for GDPR

The shortest route to a single-framework code review. Shield recognises GDPR from the wording and hands over to the GDPR specialist. A general request for a “GDPR audit” or a “compliance assessment” goes to the `privacy-advisor` workflow (an assessment of the whole privacy programme) instead: to review code, ask about named files.

**In your AI assistant**

```text
Shield, our mobile backend stores user profiles and push tokens. Review the code in services/api/ and the table definitions in db/migrations/ against the GDPR: list the personal data you find, the lawful basis you can infer for each, and the gaps.
```

**What you should get** The request goes to `gdpr-agent`, workflow 1 (code and system audit). The report follows the audit format: personal data identified, lawful-basis assessment, findings and a summary. It carries the AI-generated marking and the not-legal-advice notice.

<a id="example-shield-multi-framework-gap"></a>
### Compare two frameworks in one analysis

When a request names several frameworks, Shield runs each specialist and merges the results.

**In your AI assistant**

```text
Shield, gap analysis NIS2 vs DORA for our payment platform, which serves banks in three EU countries. We have a security incident process but no register of ICT providers. Show which obligations overlap, such as incident reporting and third-party risk, so we build one process and satisfy both, and give a prioritised remediation roadmap.
```

**What you should get** Both `nis2-agent` and `dora-agent` run, then Shield uses the cross-framework mapper (NIS2 ↔ DORA is one of the pairings it lists) to build the overlapping-control mapping and produces one consolidated report in the audit-report format: common controls (implement once, satisfy many), framework-specific gaps and a priority roadmap.

<a id="example-shield-soc2-evidence"></a>
### Prepare SOC 2 audit evidence

Use it ahead of an audit window, once you know which trust criteria are in scope.

**In your AI assistant**

```text
Shield, generate a SOC 2 evidence checklist for Security and Availability. We run on AWS with GitHub Actions. For each criterion, name the artifact to collect, who owns it and how often it must be refreshed.
```

**What you should get** Routed to `soc2-agent`, whose audit-evidence section organises evidence by criterion. Expect a checklist you can turn into tickets. It does not certify anything: only an auditor can issue a SOC 2 report.

<a id="example-shield-dpia"></a>
### Run a DPIA (dpia-sentinel)

Use it when a processing is likely to carry a high risk for people, for example the systematic monitoring of employees or profiling.

**In your AI assistant**

```text
Shield, run a DPIA for the driver-fatigue camera we are adding to our delivery vans. It films the driver’s face continuously, computes a fatigue score on the device and uploads only the score and a timestamp to the fleet dashboard. Footage stays on the device for 24 hours. Ask me for anything you need to describe the processing.
```

**What you should get** The `dpia-sentinel` workflow walks the steps of Article 35 (threshold, description, necessity and proportionality, risks, mitigation, DPO consultation, prior consultation) and produces a report in nine sections: project information, threshold assessment, processing description, necessity and proportionality, risks to data subjects, mitigation measures, DPO opinion, conclusion and sign-off. Sections 7 (DPO opinion) and 9 (sign-off) are left for the people concerned to fill in.

<a id="example-shield-breach-response"></a>
### React to a personal data breach (breach-sentinel)

Use it as soon as you suspect a breach: the 72-hour clock of Article 33 starts when you become aware of it.

**In your AI assistant**

```text
Shield, we had a data breach. An exported customer CSV (names, emails, order history, about 4,200 people in the EU) was sent to the wrong external address this morning at 09:40. Walk me through the first hours and draft the authority notification.
```

**What you should get** The `breach-sentinel` workflow follows a timeline: detection and initial assessment (first hours), severity classification, authority notification by the 72-hour mark with the four Article 33(3) elements, data-subject notice when the severity requires it, then documentation and lessons learned. The drafts are for your DPO or lawyer to review before anything is sent.

<a id="example-shield-ai-act-classification"></a>
### Classify an AI system under the AI Act

Use it first, before you decide which obligations apply. Follow with the roles and FRIA workflows when the result is high risk.

**In your AI assistant**

```text
Shield, classify my AI system under the AI Act. It ranks job applicants for a staffing agency from CVs and a short questionnaire. We build it ourselves and sell it to agencies in France and Germany.
```

**What you should get** The `ai-act-classifier` workflow identifies the system, checks the prohibited practices of Article 5, then high-risk status through Article 6 and Annex III, then limited and minimal risk, and returns a classification report with the reasoning, the applicable obligations and recommended next steps. Whether a given case is high risk is a legal conclusion: have it confirmed.

<a id="example-shield-assurance-case"></a>
### Build an assurance case tied to a commit

Use it for a release you must defend to an auditor. Run the commands from a clean working tree at the commit concerned.

**In your AI assistant**

```text
Shield, build a security assurance case for release 2.3 of our mobile API. Claims: the container image scan reports no critical vulnerability, the API refuses TLS versions below 1.2, and last night’s backup restores into an empty database. For each claim, pick a command that exits non-zero when the claim is false, then run and verify the case and tell me which claims are supported.
```

**What you should get** The case file `_bmad/assurance/<id>.yaml` is started with `bmad-plus assurance init`, `bmad-plus assurance run` executes each declared command without a shell and appends the outcome to a hash-chained ledger, and `bmad-plus assurance verify` reports each claim as supported or unsupported, judging the check behind it as passed, failed, stale or missing. Set `BMAD_PLUS_ASSURANCE_KEY` (32 characters or more) and keep the ledger head from `run` to make deliberate edits detectable. The verdict says what the evidence is; it is not a certification.

<a id="example-shield-ai-register"></a>
### Register the AI tools your project uses

Use it when you must answer which AI tools see your data and on what legal basis.

**In your AI assistant**

```text
Shield, this quarter we added a code-assistant plugin, a support-chatbot MCP server and an OCR API. Create the AI processing register, enter these three and ask me for each one’s data, legal basis, retention and any transfer outside the EU. Then check the register and tell me which integrations the scan found that I did not list.
```

**What you should get** `bmad-plus ai-register init` creates `_bmad/ai-processing-register.yaml` from the Shield template; `bmad-plus ai-register check` then prints the review date and how many AI integrations are registered, with a warning for each unregistered one (BMAD+ adapters, tool folders, MCP servers). The check is a soft gate: warnings do not make it fail, and `bmad-plus doctor` reports the same.

<a id="outputs"></a>
## What it writes and where

**Outputs of Shield and its tools**

| Path | Written by | Content |
| --- | --- | --- |
| Reports in your chat or in files you name | Shield agents | Audit, gap-analysis and workflow reports, each with the AI-generated and not-legal-advice marking |
| `_bmad/assurance/<id>.yaml` | `assurance init` | The assurance case: scope, claims, arguments, checks |
| `_bmad-output/assurance/` | `assurance run`, `verify` | Ledger of runs and the optional CI check file |
| `_bmad/ai-processing-register.yaml` | `ai-register init` | The register of AI tools and their data |
| `_bmad-output/review/<id>/` | `review scope` and later steps | Checklist opening with the controls the change touches |

<a id="data-and-prerequisites"></a>
## Data flows and prerequisites

- No Python, no API key and no extra tool: Shield is instructions plus CLI commands. Your AI tool supplies the model.
- One off-machine flow concerns the evidence commands, and it belongs to the `bmad-plus` CLI rather than to the pack: `assurance-checks`. The `assurance` command exists without Shield (the pack ships the procedure and the templates). `bmad-plus assurance run` executes the commands written in the case, with the same trust as the project’s own scripts, so a check may reach the network if its command does. Read a case written by someone else before running it. The key `BMAD_PLUS_ASSURANCE_KEY` stays in the environment and is never given to a check.
- What you paste into a Shield conversation (code, data flows, incident details) goes to your AI tool’s model like any other prompt. Do not paste live personal data into an audit request.

<a id="limits"></a>
## Limits and gotchas

> **Note · A prompt is not a certification** Specialists are expert prompts built on reference files. Their regulatory content can be out of date, and a supported claim in an assurance case means only that a named check passed at a commit. Treat every output as a draft for a qualified person.

> **Tip · Installing the pack** `--packs` takes a comma-separated list of pack ids: `npx bmad-plus install --packs core,shield`. Core is always included, and `all` installs every pack.

> **Note · Ledger limits** Without `BMAD_PLUS_ASSURANCE_KEY` and a kept `--ledger-head`, the hash chain shows accidental or careless edits only: whoever can write the ledger can append a record that verifies. Say which protection applied when you present the result.

> **Note · Provenance** The specialist agents are adapted from an MIT-licensed open-source collection of GRC skills, and the GDPR and AI Act workflows were enriched with ideas from a professional skills catalogue. The notices are in THIRD-PARTY-LICENSES.md of the package.

**See also**

- [All ten packs side by side](https://bmad-plus.rochetta.fr/docs/packs/packs-overview/)
- [assurance command reference](https://bmad-plus.rochetta.fr/docs/reference/cli-assurance/)
- [ai-register command reference](https://bmad-plus.rochetta.fr/docs/reference/cli-ai-register/)
- [review command reference](https://bmad-plus.rochetta.fr/docs/reference/cli-review/)
- [OSINT pack](https://bmad-plus.rochetta.fr/docs/packs/osint/)
- [Data handling and privacy](https://bmad-plus.rochetta.fr/docs/security/data-handling/)

[BMAD+ documentation](https://bmad-plus.rochetta.fr/docs/) · [Packs](https://bmad-plus.rochetta.fr/docs/packs/)

[Source on GitHub](https://github.com/lrochetta/BMAD-PLUS)