The Agent Skills Directory

[SAFE]: The skill operates in a read-only capacity relative to deployment data, using official toolsets to gather insights. No unauthorized data access or exfiltration patterns were detected.
[SAFE]: It implements a 'confirm-cost' gate which requires explicit user approval before executing any billable actions, preventing accidental or unauthorized expenditure.
[SAFE]: No obfuscation, prompt injection attempts, or unauthorized network communications were identified in the instructions or workflow.

convex-cost