The Agent Skills Directory

[Indirect Prompt Injection Surface]: This skill facilitates the retrieval of data from Microsoft Fabric semantic models. Processing data from external sources introduces a potential surface for indirect prompt injection if the retrieved content contains malicious instructions intended to influence the agent.
Ingestion points: Data enters the context via the result.table.rows property returned by the query() method in SKILL.md.
Boundary markers: The documentation and examples do not define explicit delimiters or instructions to ignore embedded commands within the fetched data.
Capability inventory: The FabricClient class documented in SKILL.md and references/types.md provides methods to execute DAX queries and retrieve model data.
Sanitization: No specific sanitization or validation steps are provided for the row data before it is processed by the agent.

fabric-sdk