@raishin/vanguard-frontier-agentic 2.9.0 → 2.11.0

package/skills/microsoft/power-platform-maestro/references/workflow-and-output.md

@@ -0,0 +1,86 @@
+# Routing table and domain taxonomy
+
+Use this reference when classifying a task or selecting the right specialist(s).
+
+## Domain taxonomy
+
+| Domain | Keywords and signals |
+|---|---|
+| `environment-strategy` | environment, environment type, Managed Environment, default environment, environment routing, environment groups, environment rules, developer environment, sandbox, production environment, tenant strategy, multi-environment, environment lifecycle |
+| `dlp-policy` | DLP, data loss prevention, connector classification, business data, blocked connector, tenant-wide policy, connector policy, custom connector, endpoint filtering, data policy, connector governance |
+| `dataverse-security` | Dataverse, security role, business unit, field-level security, row-level security, privilege, permission, record access, team, owner team, group team, table permission, column security |
+| `alm-pipelines` | ALM, pipeline, deployment, solution, managed solution, unmanaged solution, source control, DevOps, CI/CD, promote, stage, test environment, production deployment, solution checker, pipelines in Power Platform |
+| `connector-risk` | connector, custom connector, HTTP connector, Power Automate connector, skill connector, channel connector, Teams connector, SharePoint connector, unauthenticated connector, connector action, advanced connector policy, ACP |
+| `citizen-dev-guardrails` | citizen developer, maker, low-code, governance, CoE, Center of Excellence, app catalog, sharing, app sharing, flow sharing, Managed Environments sharing limits, maker portal, default environment security |
+| `live-guard` | deploy to production, production deployment, tenant-wide DLP change, DLP policy tenant scope, production environment change, requires human gate |
+
+## Full routing table
+
+### Environment Strategy
+
+| Agent | Domain(s) | Use when… |
+|---|---|---|
+| `power-platform-solution-architect-agent` | environment-strategy | Designing or reviewing a Power Platform tenant environment strategy, multi-environment topology, or governance framework |
+| `power-platform-governance-environment-strategy-lead` | environment-strategy, citizen-dev-guardrails | Leading environment strategy decisions, defining environment types, Managed Environments, environment groups and rules, default environment security |
+
+### DLP Policy
+
+| Agent | Domain(s) | Use when… |
+|---|---|---|
+| `power-platform-governance-environment-strategy-lead` | dlp-policy, environment-strategy | Designing or reviewing DLP policy strategy, connector classification tiers, tenant-level vs environment-level policy scope |
+| `power-automate-automation-risk-reviewer` | dlp-policy, connector-risk | Reviewing DLP policy impact on Power Automate flows, connector risk in existing automations, or evaluating connector change risk |
+
+### Dataverse Security
+
+| Agent | Domain(s) | Use when… |
+|---|---|---|
+| `dataverse-security-model-architect` | dataverse-security | Designing or reviewing Dataverse security roles, business unit hierarchy, field-level security, row-level security, or privilege scope |
+| `power-platform-solution-architect-agent` | dataverse-security, environment-strategy | Reviewing cross-environment Dataverse security design as part of a broader solution architecture |
+
+### ALM / Pipelines
+
+| Agent | Domain(s) | Use when… |
+|---|---|---|
+| `power-platform-alm-pipelines-engineer` | alm-pipelines | Designing, implementing, or troubleshooting Power Platform ALM pipelines, solution promotion, solution checker, or DevOps integration |
+| `power-platform-solution-architect-agent` | alm-pipelines, environment-strategy | Reviewing ALM pipeline topology as part of a broader multi-environment architecture |
+
+### Connector Risk
+
+| Agent | Domain(s) | Use when… |
+|---|---|---|
+| `power-automate-automation-risk-reviewer` | connector-risk, dlp-policy | Reviewing connector risk in Power Automate flows, assessing impact of connector changes, or evaluating unauthenticated/HTTP connector usage |
+| `power-platform-governance-environment-strategy-lead` | connector-risk, dlp-policy | Reviewing tenant-wide connector governance policy, advanced connector policies (ACP), or channel publishing restrictions in Copilot Studio |
+
+### Citizen Dev Guardrails
+
+| Agent | Domain(s) | Use when… |
+|---|---|---|
+| `power-platform-governance-environment-strategy-lead` | citizen-dev-guardrails, environment-strategy | Establishing citizen developer guardrails, CoE strategy, sharing limits, app catalog governance, or maker onboarding controls |
+| `power-platform-solution-architect-agent` | citizen-dev-guardrails | Reviewing low-code governance as part of a broader platform solution design |
+
+### Live-guard (ALWAYS requires human gate)
+
+| Agent | Domain(s) | Use when… |
+|---|---|---|
+| `power-platform-alm-pipelines-engineer` | live-guard, alm-pipelines | Deploying a solution to a PRODUCTION environment via pipeline — requires blast-radius assessment, rollback path, and explicit human confirmation |
+| `power-platform-governance-environment-strategy-lead` | live-guard, dlp-policy | Applying a tenant-wide DLP policy change — requires blast-radius assessment, rollback path, and explicit human confirmation |
+
+## Live-guard gate protocol
+
+Before routing to any live-guard operation, surface all three and wait for explicit written confirmation:
+
+1. **Blast-radius assessment** — what environments, flows, apps, or users are affected if this goes wrong?
+2. **Rollback path** — what is the tested rollback procedure and estimated recovery time?
+3. **Explicit confirmation** — "I confirm I understand the blast radius and rollback path. Proceed."
+
+If the user cannot supply a rollback path, recommend routing to `power-platform-solution-architect-agent` first to develop the rollback plan.
+
+## Response shape
+
+Every Maestro response begins with the routing header:
+```
+Route: <agent-name(s)>
+Reason: <one sentence>
+Mode: <single | parallel (N specialists) | live-guard-gate>
+```
+Followed by: dispatched specialist output (summarized), then recommended next actions.

package/skills/netsuite/README.md

@@ -0,0 +1,138 @@
+# Oracle NetSuite Skills
+
+Companion skill library for the 25 NetSuite agents. Each skill provides procedures, decision logic, safety checklists, and least-privilege guidance.
+
+## Portfolio Overview
+
+**25 skills** (1:1 with agents):
+- Layer 1 Governance & Routing (5)
+- Layer 2 Domain Specialists (20)
+
+Each skill includes:
+- `SKILL.md` – Description, when-to-use, workflow, safety rules, decision logic
+- `metadata.json` – Catalog metadata (id, name, provider, harnesses, allowed-tools, etc.)
+- `references/` – Official sources, safety checklists, least-privilege notes, release drift, topic-specific guides
+
+## Key Features
+
+### Evidence Hierarchy
+Skills declare evidence quality per step:
+1. LIVE_EVIDENCE (NetSuite live API, current state)
+2. REPOSITORY_EVIDENCE (project git, version control)
+3. USER_PROVIDED (context from engineer)
+4. OFFICIAL_DOCUMENTATION (NetSuite/Oracle docs + date)
+5. INFERENCE (agent reasoning)
+6. UNVERIFIED (claims without source)
+7. BLOCKED (denied—credentials, live mutations, fabrications)
+
+### Least Privilege by Default
+Each skill's `references/least-privilege.md` provides:
+- Standard role baseline
+- Permission removal checklist
+- Module requirements
+- 2FA mandate for privileged roles
+- Forbidden permission combinations
+
+### Release Sensitivity
+Skills track NetSuite's biannual release timeline:
+- 2026.1 – OAuth2 default, SOAP deprecation
+- 2027.1 – New SOAP integrations disabled
+- 2028.2 – SOAP sunset (estimated)
+
+Claims impacting future releases are labeled explicitly.
+
+### Safety Checklists
+Each `references/safety-checklist.md` covers:
+- Refusal triggers (credentials, live mutations, admin role)
+- Escalation gates (cross-domain, segregation of duties, etc.)
+- Evidence quality gates
+- Compliance and audit trails
+
+## Companion to Agents
+
+Each skill is paired with its agent:
+- Agent performs judgment and review
+- Skill provides step-by-step procedure and safety rules
+- Together they form a complete advisory capability
+
+Example: `netsuite-sso-oauth-tba-agent` + `netsuite-sso-oauth-tba-skill`
+- Agent: "This design uses TBA. Is that optimal given your integrations?"
+- Skill: "TBA use cases, OAuth2 preference, token management, 2FA requirements, release timeline…"
+
+## Routing & Cross-Domain
+
+The cross-functional `netsuite-routing-protocol` skill coordinates:
+- Multi-domain escalations (saved-search + oneworld + data-governance, etc.)
+- Conflict resolution when agents disagree
+- Escalation gates (segregation-of-duties, irreversible-deploy, finance/revenue, etc.)
+
+Skills reference this protocol when matters cross boundaries.
+
+## Official Sources
+
+All skills cite official NetSuite/Oracle sources with verification dates:
+- NetSuite Certification Resource Center
+- Oracle NetSuite Help Portal
+- SuiteTalk API documentation
+- SuiteCloud SDK github
+- Release notes and breaking-change bulletins
+
+No fabrication. All facts trace back to official docs.
+
+## Files
+
+- `netsuite/<agent-id>-skill/` – Individual skill directories
+  - `SKILL.md` – Main skill spec (allowed-tools in frontmatter)
+  - `metadata.json` – Catalog metadata
+  - `references/official-sources.md` – Citation list with URLs and dates
+  - `references/safety-checklist.md` – Refusal triggers, escalation gates, evidence quality
+  - `references/least-privilege.md` – Role, permission, 2FA, module guidance
+  - `references/release-drift.md` – NetSuite release timeline and impacts
+  - `references/<topic>.md` – Topic-specific guides (e.g., sandbox-oauth-isolation.md)
+
+## No Live Mutations
+
+Skills are advisory and procedural ONLY. They do NOT:
+- Deploy to production
+- Modify permissions or roles in live accounts
+- Execute workflows
+- Edit data
+- Activate features
+
+Live actions require `netsuite-live-org-mutation-guard-agent` + separate human authorization.
+
+## Least-Privilege Baseline
+
+Skills enforce:
+- Never Administrator unless scoping requires it (then document removal plan)
+- 2FA on all privileged custom roles
+- OAuth2 for REST/RESTlets/SuiteAnalytics; TBA only as fallback
+- No user credentials; service accounts with OAuth2 tokens
+- Minimum-necessary modules and permissions per role
+
+## Escalation & Conflict Resolution
+
+When matters cross domains or agents disagree:
+1. netsuite-routing-protocol applies conflict-resolution protocol
+2. Escalation gate fires (e.g., segregation-of-duties, irreversible-deploy)
+3. Matter pauses and escalates to human owner
+4. Decision logged in audit trail
+
+Skills document escalation triggers and gates explicitly.
+
+## Tools & Boundaries
+
+Each skill declares `allowed-tools` in SKILL.md frontmatter:
+- Read – read project files, official docs
+- Grep – search code and specs
+- Glob – find files by pattern
+- **NOT** allowed by default: Bash, GitHub mutation, live NetSuite API calls
+
+This enforces the advisory boundary: judgment without destructive capability.
+
+---
+
+**Version:** 0.1.0  
+**Provider:** netsuite  
+**Source:** github: Raishin  
+**Last updated:** 2026-06-09

package/skills/netsuite/netsuite-administrator-skill/SKILL.md

@@ -0,0 +1,85 @@
+---
+name: netsuite-administrator-skill
+description: "Flashlight skill for reviewing NetSuite account administration configurations aligned to the Administrator Professional certification (N16291GC10). T0 static review — no live account connection required, never Administrator role. TRIGGER when: user asks to review accounting preferences, tax nexus setup, currency management, user provisioning policy, email template defaults, sandbox refresh procedures, release preview planning, or account-level system preferences in NetSuite. Trigger phrases: review account setup, audit user provisioning, check accounting preferences, validate tax configuration, sandbox refresh checklist, release preview prep, administrator review. DO NOT TRIGGER when: request concerns OAuth 2.0 or TBA authentication flows (use netsuite-sso-oauth-tba-agent), role permission and SoD matrix design (use netsuite-identity-access-role-permission-agent), financial close controls or posting periods (use netsuite-financial-foundations-agent), SuiteScript code review (use netsuite-application-developer-agent), or any live mutation in a production account is requested."
+allowed-tools: Read Grep Glob
+metadata:
+  author: "github: Raishin"
+  version: "0.1.0"
+  updated: "2026-06-09"
+  category: platform
+  lifecycle: experimental
+  execution_tier: static-review
+  mcp_servers: []
+  oauth_scopes: []
+  run_as_permissions:
+    required: []
+    denied: []
+---
+
+# NetSuite Administrator Skill
+
+## Purpose
+
+Validates enterprise-grade NetSuite account administration decisions and settings that require Administrator Professional-level depth (N16291GC10) but are executed through least-privilege custom roles, never via the Administrator role itself. Surfaces misconfigurations in account preferences, tax engine setup, user access controls, and sandbox lifecycle governance that carry outsized compliance and operational risk in Fortune-50 deployments. T0 static review — no NetSuite account connection required; output is a draft for human review.
+
+## When This Skill Owns the Task
+
+- Enterprise implementation team needs account-level administration configurations reviewed before go-live
+- CoE or IT governance team submits accounting preferences, tax setup, or user provisioning policies for audit
+- Fortune-50 administrator needs sandbox refresh governance documentation reviewed for OAuth 2.0 re-authorization compliance
+- Release preview impact assessment is needed for an upcoming NetSuite version upgrade
+
+## Recommended Workflow
+
+1. Step 1 — Collect sanitized inputs: accounting preferences export, tax nexus summary, currency settings, user provisioning template, and sandbox refresh runbook
+2. Step 2 — Review accounting preferences: fiscal year alignment, period management defaults, accounting impact settings, and GL preferences
+3. Step 3 — Audit tax and currency: validate nexus completeness, tax engine selection rationality, base currency correctness, and exchange rate source configuration
+4. Step 4 — Evaluate user provisioning: role assignment patterns, 2FA designation for sensitive roles, separation of concerns in provisioning workflow
+5. Step 5 — Assess sandbox and release posture: verify OAuth 2.0 re-authorization procedures exist for post-refresh environments; identify SOAP integration deprecation risks against 2026.1–2028.2 timeline
+6. Step 6 — Emit findings report: rated Critical / High / Medium / Low with [FACT] / [INFERENCE] / [ASSUMPTION] labels, explicit Administrator-role prohibition reminders, and safe-next-actions for each finding
+
+## Evidence Hierarchy
+
+LIVE_EVIDENCE > REPOSITORY_EVIDENCE > USER_PROVIDED > OFFICIAL_DOCUMENTATION > INFERENCE > UNVERIFIED > BLOCKED
+
+## Safety Checklist
+
+- No live NetSuite connection — all inputs are sanitized configuration excerpts only
+- No credentials, tokens, passwords, or consumer keys in submitted inputs
+- Administrator role never recommended under any circumstances
+- 2FA designation verified for all roles holding sensitive administrative permissions
+- Sandbox refresh runbook includes OAuth 2.0 re-authorization checklist (evidence-matrix rows 8a, 8b)
+- SOAP deprecation risk surfaced if any integration is identified as SOAP-based
+
+## Rules — Hard-Stop Constraints
+
+- Static review only; never connect to a live NetSuite account or invoke APIs/SuiteScript/SDF.
+- Never request or accept credentials, tokens, or secrets.
+- Never depend on the Administrator role; recommend least-privilege custom roles (note 2FA).
+- Prefer OAuth 2.0 (REST/RESTlets/SuiteAnalytics Connect) over SOAP; treat SOAP as a migration risk.
+- Never claim a Coming-Soon certification is available.
+
+## Refusal Triggers
+
+- Input contains credentials, tokens, consumer keys, client secrets, passwords, or any authentication material — stop and require sanitization before resubmitting
+- Request involves executing, deploying, or activating any configuration change in a live or production account
+- Request to use or recommend the Administrator role for any purpose — an absolute refusal; cite evidence-matrix rows 7a and 7b
+- Request to connect, authenticate, or log in to any NetSuite environment
+- Claim that AI Specialist or AI Professional certifications are available — those are COMING SOON; only AI Foundations Associate (N16765GC10) is currently available
+- Request to approve production-environment changes without documented sandbox validation evidence
+
+## T0 Contract
+
+No account connection, no OAuth, no secrets. Output is draft review text for a human owner.
+
+## Security Notes
+
+Static review only — works exclusively from sanitized configuration exports; never requests or accepts credentials, tokens, session IDs, consumer keys, or any authentication material. Does not connect to, query, or mutate any NetSuite account. The Administrator role is absolutely prohibited — custom roles are always derived from standard roles with View-only permissions. OAuth 2.0 sandbox isolation requirements (re-authorization after each refresh) are surfaced in every sandbox governance review. SOAP deprecation risks (2026.1 / 2027.1 / 2028.2 milestones) are flagged for any integration posture identified during review.
+
+## Reference File Index
+
+- [official-sources.md](references/official-sources.md) — Oracle NetSuite Administrator Professional certification and help URLs from evidence-matrix
+- [safety-checklist.md](references/safety-checklist.md) — Pre-submission sanitization and least-privilege custom role construction checklist
+- [least-privilege.md](references/least-privilege.md) — Custom role derivation pattern for administrative reviewer — never Administrator role
+- [release-drift.md](references/release-drift.md) — SOAP removal timeline (2026.1 / 2027.1 / 2028.2) and OAuth 2.0 default migration impact
+- [sandbox-oauth-isolation.md](references/sandbox-oauth-isolation.md) — OAuth 2.0 and TBA token isolation rules for sandbox and Release Preview environments

package/skills/netsuite/netsuite-administrator-skill/metadata.json

@@ -0,0 +1,36 @@
+{
+  "id": "netsuite-administrator-skill",
+  "name": "NetSuite Administrator Skill",
+  "type": "skill",
+  "provider": "netsuite",
+  "harnesses": [
+    "claude-code",
+    "codex",
+    "cursor",
+    "gemini",
+    "kiro",
+    "other"
+  ],
+  "summary": "Flashlight skill for reviewing NetSuite account administration configurations aligned to the Administrator Professional certification (N16291GC10). T0 static review — no live account connection required, never Administrator role. TRIGGER when: user asks to review accounting preferences, tax nexus se",
+  "source_type": "original",
+  "category": "platform",
+  "execution_tier": "static-review",
+  "oauth_scopes": [],
+  "mcp_servers": [],
+  "run_as_permissions": {},
+  "sandbox_only": false,
+  "production_allowed": true,
+  "official_docs": [
+    "https://education.oracle.com/oracle-netsuite-administrator-professional/pexam_N16291GC10",
+    "https://www.netsuite.com/portal/services/training/suite-training/netsuite-certification.shtml",
+    "https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/section_N285436.html",
+    "https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/section_1532968056.html",
+    "https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/section_157771979135.html",
+    "https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/article_2104046421.html"
+  ],
+  "security_notes": "Static review only — works exclusively from sanitized configuration exports; never requests or accepts credentials, tokens, session IDs, consumer keys, or any authentication material. Does not connect to, query, or mutate any NetSuite account. The Administrator role is absolutely prohibited — custom roles are always derived from standard roles with View-only permissions. OAuth 2.0 sandbox isolation requirements (re-authorization after each refresh) are surfaced in every sandbox governance review. SOAP deprecation risks (2026.1 / 2027.1 / 2028.2 milestones) are flagged for any integration posture identified during review.",
+  "last_verified": "2026-06-09",
+  "path": "skills/netsuite/netsuite-administrator-skill",
+  "author": "github: Raishin",
+  "version": "0.1.0"
+}

package/skills/netsuite/netsuite-administrator-skill/references/least-privilege.md

@@ -0,0 +1,66 @@
+# Least-privilege NetSuite posture for NetSuite Administrator Agent
+
+## Execution tier
+
+**T0 — Static Review**
+
+Rationale: `execution_tier: "static-review"` declared in `metadata.json`. This agent reviews sanitized configuration excerpts and never holds a live NetSuite session.
+
+## Identity model
+
+No live NetSuite identity is required for the agent itself. When a human operator acts on this agent's review, they SHOULD use the least-privilege custom role below — never the Administrator role.
+
+## Recommended custom role
+
+- **Custom role name:** NetSuite Administrator Reviewer (custom)
+- **Copy from standard role:** Full Access (read-only copy, stripped of all Edit/Create/Full levels) (NetSuite guidance: start from a copy of a standard role, then remove unneeded permissions).
+- **Modules in scope:** Core Administration, Company Preferences, Currency Management, User Management, Email Management
+- **Two-Factor Authentication required:** Yes
+
+### Minimal permissions
+
+- **Company Information** (View) — Inspect legal entity, tax registration, and nexus settings
+- **Accounting Preferences** (View) — Review fiscal year, period, and accounting impact defaults
+- **Currency** (View) — Review base currency, multi-currency, and exchange rate source settings
+- **Manage Users** (View) — Review user provisioning patterns and role assignment without editing user records
+- **Setup** (View) — Review page layout, tab customization, and system preferences
+- **Email Preferences** (View) — Inspect email template defaults and bounce handling settings
+- **Sandbox Management** (View) — Review sandbox environment list and refresh history (no initiation rights)
+
+## Forbidden
+
+- Administrator role — absolute prohibition regardless of context
+- Edit or Full level on any Setup or Users/Roles page
+- Access Token Management permission
+- OAuth 2.0 Authorized Applications Management permission
+- Core Administration Permissions bundle
+
+## Blast-radius bound
+
+Even if fully compromised, this agent cannot mutate a NetSuite account: it has no live session, no API tokens, and no SDF deploy rights. It can only produce review text.
+
+## Refusal triggers
+
+- Input contains credentials, tokens, consumer keys, client secrets, passwords, or any authentication material — stop and require sanitization before resubmitting
+- Request involves executing, deploying, or activating any configuration change in a live or production account
+- Request to use or recommend the Administrator role for any purpose — an absolute refusal; cite evidence-matrix rows 7a and 7b
+- Request to connect, authenticate, or log in to any NetSuite environment
+- Claim that AI Specialist or AI Professional certifications are available — those are COMING SOON; only AI Foundations Associate (N16765GC10) is currently available
+- Request to approve production-environment changes without documented sandbox validation evidence
+
+## Escalation path
+
+Route all live-account changes to `netsuite-live-org-mutation-guard-agent` with a named human decision owner and a structured case capsule.
+
+## Role creation steps
+
+1. In the target SANDBOX, copy the standard role named above to a new custom role.
+2. Remove every permission not listed under Minimal permissions.
+3. Add only the listed permissions at the stated access level.
+4. Confirm the role is NOT Administrator and grants no global/cross-subsidiary access beyond remit.
+5. Enable 2FA enforcement if the role touches privileged permissions.
+6. Test in sandbox, then assign to the integration/review user; monitor for least-privilege drift.
+
+## Companion skill
+
+`netsuite-administrator-skill` — NetSuite Administrator Skill

package/skills/netsuite/netsuite-administrator-skill/references/official-sources.md

@@ -0,0 +1,12 @@
+# Official Sources
+
+Oracle NetSuite Administrator Professional certification and help URLs from evidence-matrix
+
+Verified 2026-06-09 against official Oracle/NetSuite documentation:
+
+- https://education.oracle.com/oracle-netsuite-administrator-professional/pexam_N16291GC10
+- https://www.netsuite.com/portal/services/training/suite-training/netsuite-certification.shtml
+- https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/section_N285436.html
+- https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/section_1532968056.html
+- https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/section_157771979135.html
+- https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/article_2104046421.html

package/skills/netsuite/netsuite-administrator-skill/references/release-drift.md

@@ -0,0 +1,11 @@
+# Release Drift
+
+SOAP removal timeline (2026.1 / 2027.1 / 2028.2) and OAuth 2.0 default migration impact
+
+NetSuite releases biannually. Content verified 2026-06-09.
+
+Release-sensitive items to re-verify each release:
+
+- SOAP web services removal timeline (REST + OAuth 2.0 recommended for new integrations from 2026.1; new SOAP integrations blocked at 2027.1).
+- Certification availability (AI Specialist/Professional and BI & Reporting Professional are Coming Soon — re-check status).
+- AI Connector / MCP permission names and role restrictions.

package/skills/netsuite/netsuite-administrator-skill/references/safety-checklist.md

@@ -0,0 +1,19 @@
+# Safety Checklist
+
+Pre-submission sanitization and least-privilege custom role construction checklist
+
+- No live NetSuite connection — all inputs are sanitized configuration excerpts only
+- No credentials, tokens, passwords, or consumer keys in submitted inputs
+- Administrator role never recommended under any circumstances
+- 2FA designation verified for all roles holding sensitive administrative permissions
+- Sandbox refresh runbook includes OAuth 2.0 re-authorization checklist (evidence-matrix rows 8a, 8b)
+- SOAP deprecation risk surfaced if any integration is identified as SOAP-based
+
+## Refusal triggers
+
+- Input contains credentials, tokens, consumer keys, client secrets, passwords, or any authentication material — stop and require sanitization before resubmitting
+- Request involves executing, deploying, or activating any configuration change in a live or production account
+- Request to use or recommend the Administrator role for any purpose — an absolute refusal; cite evidence-matrix rows 7a and 7b
+- Request to connect, authenticate, or log in to any NetSuite environment
+- Claim that AI Specialist or AI Professional certifications are available — those are COMING SOON; only AI Foundations Associate (N16765GC10) is currently available
+- Request to approve production-environment changes without documented sandbox validation evidence

package/skills/netsuite/netsuite-administrator-skill/references/sandbox-oauth-isolation.md

@@ -0,0 +1,14 @@
+# Sandbox Oauth Isolation
+
+OAuth 2.0 and TBA token isolation rules for sandbox and Release Preview environments
+
+Scope: Validates enterprise-grade NetSuite account administration decisions and settings that require Administrator Professional-level depth (N16291GC10) but are executed through least-privilege custom roles, never via the Administrator role itself. Surfaces misconfigurations in account preferences, tax engine setup, user access controls, and sandbox lifecycle governance that carry outsized compliance and operational risk in Fortune-50 deployments.
+
+- Accounting preferences review — fiscal year setup, period management preferences, default accounting impact settings
+- Company information and tax configuration — legal entity registration, nexus setup, tax engine selection and preferences
+- Currency and exchange rate management — base currency, multi-currency preferences, exchange rate sources
+- User provisioning review — employee record defaults, role assignment patterns, global permission flag settings
+- Email and notification management — email preferences, bulk processing defaults, bounce handling configuration
+- Page and tab customization — center tab layout, portlet arrangement, company-level defaults
+- Sandbox refresh governance — pre-refresh checklist, OAuth 2.0 re-authorization requirements, TBA token lifecycle post-refresh
+- Release preview preparation — feature flag review, deprecation impact assessment, sandbox validation planning

package/skills/netsuite/netsuite-ai-connector-mcp-skill/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: netsuite-ai-connector-mcp-skill
+description: "Flashlight skill for reviewing the security and governance posture of NetSuite AI Connector Service (MCP) deployments. Verifies exact required permissions ('MCP Server Connection' and 'Log in using OAuth 2.0 Access Tokens' — not 'Log in using Access Tokens'), confirms the connecting role is never Administrator, validates explicit tool allowlists, checks HIPAA/BAA restrictions, and reviews prompt-injection testing coverage. T0 static review — no live account connection required. Depends on Oracle upstream skill netsuite-ai-connector-instructions (UPL-1.0) for tool-selection decision trees and SuiteQL safety patterns. TRIGGER when: user asks to review AI Connector configuration, audit MCP permissions, check AI agent access to NetSuite, validate tool allowlists, review prompt injection mitigations for NetSuite AI sessions, or assess AI Connector role setup. Trigger phrases: AI Connector, MCP Server Connection, NetSuite AI Service, MCP governance, tool allowlist, prompt injection NetSuite, AI agent permissions, OAuth 2.0 Access Tokens permission. DO NOT TRIGGER when: the user needs general OAuth/TBA authentication review beyond AI Connector permissions (use netsuite-sso-oauth-tba-skill), SuiteQL query design outside AI Connector context (use netsuite-web-services-integration-skill), broader REST/SOAP integration architecture (use netsuite-integration-migration-skill), or general role/permission assignment (use netsuite-identity-access-role-permission-skill)."
+license: UPL-1.0
+allowed-tools: Read Grep Glob
+metadata:
+  author: "github: Raishin"
+  version: "0.1.0"
+  updated: "2026-06-09"
+  category: security
+  lifecycle: experimental
+  execution_tier: static-review
+  mcp_servers: []
+  oauth_scopes: []
+  run_as_permissions:
+    required: []
+    denied: []
+---
+
+# NetSuite AI Connector MCP Skill
+
+## Purpose
+
+Audits the NetSuite AI Connector Service setup for correct role/permission configuration (NOT Administrator; exactly 'MCP Server Connection' and 'Log in using OAuth 2.0 Access Tokens'), explicit tool allowlists, HIPAA/BAA restriction compliance, and prompt-injection safeguards. Combines Vanguard harness governance (routing, logging, retry) with Oracle upstream AI connector guardrails. T0 static review — no NetSuite account connection required; output is a draft for human review.
+
+## When This Skill Owns the Task
+
+- Auditing the role and permissions used by an AI Connector Service integration to confirm it is not the Administrator role
+- Verifying the two exact required permissions are present: 'MCP Server Connection' and 'Log in using OAuth 2.0 Access Tokens'
+- Reviewing whether explicit tool allowlists are defined and scoped to the minimum operations needed by the AI session
+- Checking prompt-injection testing coverage for an AI Connector integration
+- Assessing whether a healthcare account with a signed BAA is attempting AI Connector activation (blocked by Oracle policy)
+
+## Recommended Workflow
+
+1. Step 1 — Load Oracle upstream skill: read and follow netsuite-ai-connector-instructions (DEPENDENCY, UPL-1.0) for tool-selection decision trees, SuiteQL safety checklist, and SafeWords principles before proceeding
+2. Step 2 — Gather inputs: request AI Connector role permission list, feature enablement status, tool allowlist config, prompt-injection test plan, and account type indicator
+3. Step 3 — Role check: verify the AI Connector role is not the Administrator role and does not have full account permissions (evidence row 6a); any violation is Critical
+4. Step 4 — Permission check: confirm exactly 'MCP Server Connection' (6b) and 'Log in using OAuth 2.0 Access Tokens' (6c) are present; flag confusion with 'Log in using Access Tokens' as a finding
+5. Step 5 — Feature check: confirm Server SuiteScript, OAuth 2.0 enabled; confirm REST Web Services enabled if MCP Standard Tools SuiteApp is used (6d)
+6. Step 6 — Tool allowlist and prompt-injection review: assess explicitness of tool allowlist; assess presence and coverage of prompt-injection test cases; flag gaps as High
+7. Step 7 — HIPAA/BAA check: if account is healthcare with signed BAA, flag as Critical (6e); emit structured findings report with verdict, findings table, safe next actions, and escalation triggers
+
+## Evidence Hierarchy
+
+LIVE_EVIDENCE > REPOSITORY_EVIDENCE > USER_PROVIDED > OFFICIAL_DOCUMENTATION > INFERENCE > UNVERIFIED > BLOCKED
+
+## Safety Checklist
+
+- No live NetSuite credentials, tokens, or session cookies accepted
+- AI Connector role must never be Administrator or full-permission role — Critical if present
+- Exact permission names must match verbatim: 'MCP Server Connection' and 'Log in using OAuth 2.0 Access Tokens'
+- HIPAA/BAA healthcare accounts must not activate AI Connector — Critical if attempted
+- Tool allowlist must be explicit — implicit full access is a High finding
+- All findings labeled [FACT], [ASSUMPTION], or [INFERENCE] with source config reference
+
+## Rules — Hard-Stop Constraints
+
+- Static review only; never connect to a live NetSuite account or invoke APIs/SuiteScript/SDF.
+- Never request or accept credentials, tokens, or secrets.
+- Never depend on the Administrator role; recommend least-privilege custom roles (note 2FA).
+- Prefer OAuth 2.0 (REST/RESTlets/SuiteAnalytics Connect) over SOAP; treat SOAP as a migration risk.
+- Never claim a Coming-Soon certification is available.
+
+## Refusal Triggers
+
+- Request provides live NetSuite credentials, session tokens, TBA tokens, OAuth client secrets, or admin passwords — refuse immediately, do not log or echo
+- Request asks the agent to use the Administrator role or any role with full permissions to access NetSuite features for AI Connector configuration (evidence row 6a)
+- Request asks the agent to directly activate, modify, or disable the AI Connector Service in a live account
+- Request uses 'Log in using Access Tokens' instead of 'Log in using OAuth 2.0 Access Tokens' and asserts they are equivalent — they are NOT equivalent (evidence row 6c); flag and correct
+- Request claims AI Specialist or AI Professional certifications are currently available — they are COMING SOON only (evidence rows 1b, AI track)
+- Request attempts to configure the AI Connector for a healthcare account with a signed BAA — blocked by Oracle policy (evidence row 6e)
+
+## T0 Contract
+
+No account connection, no OAuth, no secrets. Output is draft review text for a human owner.
+
+## Security Notes
+
+Static review only. This agent never requests, stores, echoes, or logs NetSuite credentials, OAuth tokens, TBA tokens, client secrets, or session cookies. The AI Connector role reviewed must never be the Administrator role (evidence row 6a). Exact permission names are critical: 'MCP Server Connection' and 'Log in using OAuth 2.0 Access Tokens' (evidence rows 6b, 6c). HIPAA/BAA healthcare accounts cannot use the AI Connector (evidence row 6e). All live-mutation paths are hard-routed to netsuite-live-org-mutation-guard-agent. No org connection is established at any point.
+
+## Reference File Index
+
+- [official-sources.md](references/official-sources.md) — Oracle NetSuite AI Connector Required Features and Permissions page URLs (evidence rows 6a-6e)
+- [safety-checklist.md](references/safety-checklist.md) — Pre-review checklist for AI Connector role, permissions, features, and HIPAA/BAA status
+- [least-privilege.md](references/least-privilege.md) — Custom reviewer role and AI Connector role minimum-permission specifications
+- [release-drift.md](references/release-drift.md) — AI Connector feature changes by NetSuite release that may affect MCP governance posture
+- [prompt-injection-patterns.md](references/prompt-injection-patterns.md) — Reference patterns for prompt-injection testing and SafeWords mitigations in NetSuite AI Connector sessions

package/skills/netsuite/netsuite-ai-connector-mcp-skill/metadata.json

@@ -0,0 +1,36 @@
+{
+  "id": "netsuite-ai-connector-mcp-skill",
+  "name": "NetSuite AI Connector MCP Skill",
+  "type": "skill",
+  "provider": "netsuite",
+  "harnesses": [
+    "claude-code",
+    "codex",
+    "cursor",
+    "gemini",
+    "kiro",
+    "other"
+  ],
+  "summary": "Flashlight skill for reviewing the security and governance posture of NetSuite AI Connector Service (MCP) deployments. Verifies exact required permissions ('MCP Server Connection' and 'Log in using OAuth 2.0 Access Tokens' — not 'Log in using Access Tokens'), confirms the connecting role is never Ad",
+  "source_type": "adapted",
+  "category": "security",
+  "execution_tier": "static-review",
+  "oauth_scopes": [],
+  "mcp_servers": [],
+  "run_as_permissions": {},
+  "sandbox_only": false,
+  "production_allowed": true,
+  "official_docs": [
+    "https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/section_0714080625.html",
+    "https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/article_4160616848.html",
+    "https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/section_157780312610.html",
+    "https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/section_1532968056.html",
+    "https://docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/section_N285436.html"
+  ],
+  "security_notes": "Static review only. This agent never requests, stores, echoes, or logs NetSuite credentials, OAuth tokens, TBA tokens, client secrets, or session cookies. The AI Connector role reviewed must never be the Administrator role (evidence row 6a). Exact permission names are critical: 'MCP Server Connection' and 'Log in using OAuth 2.0 Access Tokens' (evidence rows 6b, 6c). HIPAA/BAA healthcare accounts cannot use the AI Connector (evidence row 6e). All live-mutation paths are hard-routed to netsuite-live-org-mutation-guard-agent. No org connection is established at any point.",
+  "last_verified": "2026-06-09",
+  "path": "skills/netsuite/netsuite-ai-connector-mcp-skill",
+  "author": "github: Raishin",
+  "version": "0.1.0",
+  "source_attribution": "Adapted from oracle/netsuite-suitecloud-sdk packages/agent-skills/netsuite-ai-connector-instructions (Universal Permissive License UPL-1.0; Copyright (c) 2019, 2023 Oracle and/or its affiliates; https://oss.oracle.com/licenses/upl). Oracle upstream skill provides tool-selection decision trees, SuiteQL safety checklist, output formatting standards, multi-subsidiary/multi-currency scoping, and SafeWords security principles. Vanguard additions: harness routing and intake classification, tool-call logging and retry governance, prompt-injection testing review workflow, HIPAA/BAA restriction gate, and exact-permission-name verification gate."
+}