The Agent Skills Directory

Command Execution for Automation: The skill generates and runs Azure CLI commands to identify, assess, and migrate resources. These operations are core to the skill's utility and occur within the user's authenticated Azure environment.
External Data Processing: To facilitate migration, the skill ingests existing application settings and configurations. This constitutes an indirect prompt injection surface: (1) Ingestion points: Data is collected via commands in references/services/functions/automation.md; (2) Boundary markers: There are no explicit markers or warnings used when incorporating this data into the workflow; (3) Capability inventory: The skill has broad capabilities including shell execution and resource modification; (4) Sanitization: The skill does not demonstrate specific sanitization or validation of the ingested configuration values.
Identity-First Security: The skill promotes high-security standards by guiding users toward Managed Identities and identity-based access, which reduces the risk associated with static credentials.
Operational Safeguards: The workflow includes specific rules that require human confirmation for destructive actions like deleting or stopping existing applications, ensuring the user maintains control over the migration process.

azure-upgrade