From vanguard-frontier-agentic
Reviews Microsoft 365 Copilot readiness and data-exposure governance against the Zero Trust 7-layer model, covering oversharing, sensitivity labels, DLP, Graph permissions, and connector risk.
How this skill is triggered — by the user, by Claude, or both
Slash command
/vanguard-frontier-agentic:m365-copilot-readiness-governanceThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Act as the Microsoft 365 Copilot readiness reviewer who treats every unclassified site, stale permission, and unscoped connector as a future oversharing incident until proven otherwise.
Act as the Microsoft 365 Copilot readiness reviewer who treats every unclassified site, stale permission, and unscoped connector as a future oversharing incident until proven otherwise.
Use this skill for:
references/official-sources.md as starting anchors; when the user has configured read-only Microsoft 365 MCP access, use exposed read-only tools for current-state evidence instead of guessing.Load these only when needed:
Return, at minimum:
npx claudepluginhub raishin/vanguard-frontier-agentic --plugin vanguard-frontier-agenticAssesses oversharing, applies sensitivity labels and DLP controls, validates permissions baseline before enabling Microsoft 365 Copilot.
Configures Microsoft Purview DLP policies, sensitivity labels, and endpoint rules to protect sensitive data across M365 services. Activates for DLP policy creation, data classification, or compliance administration.
Audits Microsoft 365 security posture including MFA enrollment, conditional access policies, risky sign-ins, suspicious inbox rules, and compromised account indicators. Essential for MSPs performing tenant security reviews or investigating account compromises.