The Agent Skills Directory

[External Data Processing]: The skill enables the agent to read contents from Azure Storage blobs using the storage_blob_get command. When processing data from external sources, there is a security consideration regarding indirect prompt injection, where instructions embedded in a blob could attempt to influence the agent's behavior.
Ingestion points: Blob content retrieved via storage_blob_get and az storage blob download (SKILL.md).
Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the processed blob content.
Capability inventory: The skill can execute shell commands via the Azure CLI (az storage) and perform file system operations (download/upload).
Sanitization: No explicit sanitization or validation of the retrieved blob content is described in the skill instructions.
[Management Command Execution]: The skill utilizes the Azure CLI (az storage) to perform administrative tasks such as listing accounts, managing containers, and transferring files. These commands execute within the user's authenticated environment and can modify or retrieve cloud resources.
[Dependency Management]: The skill references several official Azure SDK packages for various programming languages (Python, Node.js, Java, etc.). These references point to standard, well-known libraries used for integrating with Azure services.

azure-storage