it-ops-orchestrator
Analysis
This instruction-only IT orchestration skill appears coherent and benign, but users should review any generated IT automation and be aware that task context may be routed to specialist agents.
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.
Prefer **PowerShell-first** when... The task involves automation... Example 1 – “Audit stale AD users and disable them”
The skill may produce or route advice for IT automation that can affect accounts or infrastructure. This is aligned with its stated IT-ops purpose and is paired with safety guidance, but the operational impact is worth noticing.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Assign each sub-problem to the correct agent... Manage context between agents to avoid contradicting guidance
The skill explicitly coordinates work and context across other agents. This is central to its orchestrator purpose, but the artifacts do not define detailed data-boundary rules for what context should or should not be shared.