Security Bluebook Builder
Overview
Build a minimal but real security policy for sensitive apps. The output is a single, coherent Blue Book document using MUST/SHOULD/CAN language, with explicit assumptions, scope, and security gates.
Workflow
1) Gather inputs (ask only if missing)
Collect just enough context to fill the template. If the user has not provided details, ask up to 6 short questions:
- What data classes are handled (PII, PHI, financial, tokens, content)?
- What are the trust boundaries (client/server/third parties)?
- How do users authenticate (OAuth, email/password, SSO, device sessions)?
- What storage is used (DB, object storage, logs, analytics)?
- What connectors or third parties are used?
- Retention and deletion expectations (default + user-initiated)?
If the user cannot answer, proceed with safe defaults and mark TODOs.
2) Draft the Blue Book
Load references/bluebook_template.md and fill it with the provided details. Keep it concise, deterministic, and enforceable.
3) Enforce guardrails
- Do not include secrets, tokens, or internal credentials.
- If something is unknown, write "TODO" plus a clear assumption.
- Fail closed: if a capability is required but unavailable, call it out explicitly.
- Keep scope minimal; do not add features or tools beyond what the user asked for.
4) Quality checks
Confirm the Blue Book includes:
- Threat model (assumptions + out-of-scope)
- Data classification + handling rules
- Trust boundaries + controls
- Auth/session policy
- Token handling policy
- Logging/audit policy
- Retention/deletion
- Incident response mini-runbook
- Security gates + go/no-go checklist
Resources
references/bluebook_template.md
1---2name: security-bluebook-builder3description: Build a minimal but real security policy for sensitive apps. The output is a single, coherent Blue Book document using MUST/SHOULD/CAN language, with explicit assumptions, scope, and security gates.4---56# Security Bluebook Builder78## Overview9Build a minimal but real security policy for sensitive apps. The output is a single, coherent Blue Book document using MUST/SHOULD/CAN language, with explicit assumptions, scope, and security gates.1011## Workflow1213### 1) Gather inputs (ask only if missing)14Collect just enough context to fill the template. If the user has not provided details, ask up to 6 short questions:15- What data classes are handled (PII, PHI, financial, tokens, content)?16- What are the trust boundaries (client/server/third parties)?17- How do users authenticate (OAuth, email/password, SSO, device sessions)?18- What storage is used (DB, object storage, logs, analytics)?19- What connectors or third parties are used?20- Retention and deletion expectations (default + user-initiated)?2122If the user cannot answer, proceed with safe defaults and mark TODOs.2324### 2) Draft the Blue Book25Load `references/bluebook_template.md` and fill it with the provided details. Keep it concise, deterministic, and enforceable.2627### 3) Enforce guardrails28- Do not include secrets, tokens, or internal credentials.29- If something is unknown, write "TODO" plus a clear assumption.30- Fail closed: if a capability is required but unavailable, call it out explicitly.31- Keep scope minimal; do not add features or tools beyond what the user asked for.3233### 4) Quality checks34Confirm the Blue Book includes:35- Threat model (assumptions + out-of-scope)36- Data classification + handling rules37- Trust boundaries + controls38- Auth/session policy39- Token handling policy40- Logging/audit policy41- Retention/deletion42- Incident response mini-runbook43- Security gates + go/no-go checklist4445## Resources46- `references/bluebook_template.md`
nimoqup046-collab