The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external user data from formats like CSV, Excel, and JSON. While this represents a data ingestion surface, the risk is managed through explicit instructions for input validation and constraints on data usage.
Ingestion points: User-provided project data, file paths, or parameters as described in instructions.md.
Boundary markers: None explicitly defined in the instructions.
Capability inventory: Filesystem access for reading project files and exporting reports.
Sanitization: Instructions include a specific constraint to 'Validate inputs before processing'.
[COMMAND_EXECUTION]: The skill utilizes filesystem permissions, which are necessary for its core function of analyzing user-provided construction data files and providing export options for the generated insights.
[EXTERNAL_DOWNLOADS]: The documentation contains references to external industry resources such as buildingsmart.org and openconstructionestimate.com. These are informational links relevant to the construction domain and do not involve automated execution or downloads of untrusted code.

uberization-readiness