Help us improve
Share bugs, ideas, or general feedback.
From vanguard-frontier-agentic
Static reviews NetSuite role configurations, permission assignments, and Segregation-of-Duties design. Validates custom roles against standard baselines, resolves SDF permission codes, and flags SoD conflicts.
npx claudepluginhub raishin/vanguard-frontier-agentic --plugin vanguard-frontier-agenticHow this skill is triggered — by the user, by Claude, or both
Slash command
/vanguard-frontier-agentic:netsuite-identity-access-role-permission-skillThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Role structure, permission levels, and SoD conflict detection in NetSuite. Covers standard role baselines, custom role derivation, permission catalog lookup against the 684-code SDF catalog, and multi-role SoD conflict matrices. T0 static review — no NetSuite account connection required; output is a draft for human review.
Resolves NetSuite SDF permission configurations: customrole XML, permkey/permlevel values, script deployment permissions, and least-privilege role design. Validates against bundled reference data.
Audits NetSuite financial controls for SOX compliance: SoD analysis, posting periods, revenue recognition, approval workflows, audit trails.
Validates 1C (Enterprise) role Rights.xml: XML format, namespace, global flags, object types, permission names, RLS constraints, and templates. Optionally checks role metadata (UUID, name, synonym).
Share bugs, ideas, or general feedback.
Role structure, permission levels, and SoD conflict detection in NetSuite. Covers standard role baselines, custom role derivation, permission catalog lookup against the 684-code SDF catalog, and multi-role SoD conflict matrices. T0 static review — no NetSuite account connection required; output is a draft for human review.
LIVE_EVIDENCE > REPOSITORY_EVIDENCE > USER_PROVIDED > OFFICIAL_DOCUMENTATION > INFERENCE > UNVERIFIED > BLOCKED
No account connection, no OAuth, no secrets. Output is draft review text for a human owner.
Static review only — works from sanitized configuration excerpts and never requests credentials, tokens, client secrets, or user PII. Never assumes or recommends Administrator role. Every permission recommendation cites official evidence. Does not perform live role assignments or account mutations.