Reference register
Every source the prompts select from, by tier. Descriptions are this site's words; nothing is reproduced from the sources, and each source's own licence governs its use. Each entry's verification date is the date its repository page and licence file were fetched and read; an entry older than 180 days is marked for re-verification. The register as data is references.yml; how the tiers and triggers work is on the method page.
Tier 0: Conduct
| Reference | Licence | Verified | Role |
|---|---|---|---|
| AIQT Guardrails | Apache 2.0 | 2026-10-30 | Conduct standard for the assistant. |
Tier 1: Always applied
| Reference | Licence | Verified | Role |
|---|---|---|---|
| Secure Config | CC0; vendored AIQT material Apache 2.0 | 2026-10-30 | Deployment exposure per service: TLS, human and machine authentication, MFA, access restriction, secrets, inbound and outbound network access, lifecycle. |
| GRC Library | CC BY-SA 4.0 | 2026-10-30 | Governance, risk, compliance, privacy, AI governance, supply chain, secure development, resilience. |
| Whats.Going.On. (WGO) | MIT | 2026-10-30 | Prompt-first audit method starting from a business concern; selects product, technical, operational, security, continuity, and business perspectives. |
| OWASP ASVS | CC BY-SA 4.0 | 2026-10-30 | Application-layer security requirements, levelled. |
Tier 2: Applied on trigger
| Reference | Licence | Verified | Trigger | Role |
|---|---|---|---|---|
| DataGrail Privacy Assessment skill | Not read; the archive's own licence terms govern | 2026-10-30 | Personal data processed | Drafts a privacy impact assessment in a 9-section structure, screens for high-risk processing, models inherent and residual risk to individuals. |
| OWASP Top 10 for LLM Applications, including the Agentic Top 10 | CC BY-SA 4.0 | 2026-10-30 and 2026-10-31 | AI components present; agentic path when agents with tool use are present | Vulnerability taxonomy for LLM and agent components. |
| MITRE ATLAS data | Apache 2.0 | 2026-10-30 | AI components present | Adversary tactics, techniques, and case studies for AI systems, as structured data. |
| SLSA | Community Specification License 1.0 | 2026-10-30 | Artefacts consumed by others, or build integrity bears on the decision | Build integrity and provenance levels. |
| CycloneDX specification | Apache 2.0 | 2026-10-31 | Third-party dependencies with supply chain bearing on the decision | SBOM format. |
| OWASP SCVS | CC BY-SA 4.0 | 2026-10-31 | Third-party dependencies with supply chain bearing on the decision | Verification levels for components and SBOM practice. |
| OWASP SAMM | CC BY-SA 4.0 | 2026-10-30 | Decision concerns the organization | Software assurance process maturity. |
| CHAOSS metrics | MIT | 2026-10-30 | Due diligence, handover, or sustainability in the decision | Project health metrics: contributor concentration, responsiveness, release cadence. |
| Minimum Viable Secure Product | CC0 1.0 | 2026-10-31 | Project is or will be a supplier to other organizations | Short vendor-facing minimum baseline. |
| CSA Cloud Controls Matrix (CCM) | CSA terms; no licence needed for internal use, customization or commercial use needs one (CCM page, read 2026-10-31) | 2026-10-31 | Owner opts into framework alignment at planning Step 0 and supplies the copy | Cloud security control framework used, at the owner's option, to organize the plan and the report by control domain and identifier. |
| CSA AI Controls Matrix (AICM) | CSA terms; see the licensing FAQ (read 2026-10-31) | 2026-10-31 | Owner opts into framework alignment and AI components are present | AI-specific extension of the CCM used, at the owner's option, to organize AI findings by control domain and identifier. |
| OWASP Threat Modeling Playbook | CC BY-SA 4.0 | 2026-10-31 | New system, significant change, or no existing threat model | Threat modelling as a process; supplies the adversary and asset view that WGO's business view lacks. |
| Clean Language | CC BY-SA 4.0 | 2026-10-30 | Written artefacts are deliverables or will be relied on | Prose quality of the project's written artefacts only. |
| Diátaxis | CC BY-SA 4.0 | 2026-10-30 | Written artefacts are deliverables or will be relied on | Whether the right kinds of documentation exist. |
Tier 3: Supporting
| Reference | Licence | Verified | Role |
|---|---|---|---|
| OWASP Web Security Testing Guide | CC BY-SA 4.0 | 2026-10-31 | Test procedures for ASVS requirements. |
| OWASP AI Testing Guide | CC BY-SA 4.0 | 2026-10-31 | Test procedures for LLM Top 10 and ATLAS findings. |
| OWASP Cheat Sheet Series | CC BY-SA 4.0 | 2026-10-30 | Remediation guidance for Phase 5 and plan remediation sections. |
| NIST OSCAL content | US public domain | 2026-10-31 | SP 800-53 catalogues and baselines as machine-readable data; authoritative identifiers when findings are mapped to 800-53. |
Tools
| Reference | Licence | Verified | Trigger | Role |
|---|---|---|---|---|
| OpenSSF Scorecard | Apache 2.0 | 2026-10-30 | Source in a hosted git repository | Repository hygiene checks: branch protection, pinned dependencies, token permissions, signed releases. |
| Gitleaks | MIT | 2026-10-31 | Source in a hosted git repository | Secrets in repository history. |
| promptfoo | MIT | 2026-10-31 | AI components present | Prompt, agent, and RAG red teaming. |
| garak | Apache 2.0 | 2026-10-31 | AI components present | LLM vulnerability scanning. |
| kube-bench | Apache 2.0 | 2026-10-31 | Kubernetes in scope | Kubernetes configuration against the CIS Kubernetes Benchmark. |
Considered and excluded
Recorded so that the decision is not re-litigated without new information. Candidates and the reason each was excluded:
- OWASP API Security Top 10: overlaps ASVS. Reconsider as Tier 2 for API-centric projects.
- OpenSSF Security Baseline: overlaps Scorecard. Reconsider for projects that are themselves open source.
- OWASP AI Exchange: overlaps the LLM Top 10 and the GRC Library AI domain.
- OWASP Machine Learning Security Top 10: overlaps ATLAS and the LLM Top 10.
- OWASP Top 10 Privacy Risks: no top-level licence file found; DataGrail covers the workstream.
- REUSE: would cover licence compliance of the project's own code, which nothing in the register does, but no top-level licence file found. Open decision.
- Agent Control Standard: Apache 2.0; announced 1 Sept 2026. Reconsider as Tier 2 once mature.
- WCAG: accessibility; W3C Document Licence. Reconsider as Tier 2 for projects with a user-facing interface.
- CNCF TAG Security: mixed licensing. Reconsider as Tier 2 for Kubernetes deployments alongside kube-bench.
- Vale: prose linter; tooling, and would need a Clean Language rule set written for it.
- arc42: architecture documentation template; reconsider when architecture documentation is a handover deliverable.
- The Twelve-Factor App: dated operability heuristics; WGO's operational perspective covers the ground.