Entra Id Auditor
Analysis
This appears to be a read-only Entra ID audit guide, but it handles sensitive tenant identity exports that should only be shared by authorized users.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
az role assignment list --output json > role-assignments.json ... az ad app list --output json ... Remediation Steps: PowerShell / Graph API commands per finding
The skill documents Azure CLI export commands and may generate remediation commands. The artifacts frame these as user-directed and do not instruct automatic execution.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
"role": "Global Reader", "scope": "Azure AD Tenant", "note": "Also assign 'Security Reader' for Conditional Access and Identity Protection"
The audit relies on tenant-wide read roles and sensitive Entra ID exports. This is purpose-aligned and disclosed, but users should understand the breadth of directory data involved.
