The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external semantic model definitions (TMDL and .bim files) which represent untrusted data that could contain malicious instructions meant to influence agent behavior.
Ingestion points: Local file access via Read and Grep tools for TMDL files and .bim files, as well as remote metadata retrieval via the fab CLI.
Boundary markers: The skill instructions do not explicitly mandate the use of delimiters or 'ignore embedded instructions' warnings when interpolating model data into the prompt context.
Capability inventory: The skill can read local files, execute shell commands (e.g., fab, jq, and the provided validate_rules.py script), and generate C# and DAX logic.
Sanitization: No explicit sanitization, validation, or escaping of model content is described before the data is processed by the AI.

bpa-rules