The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from untrusted or external project files to automate the creation of a business model.
Ingestion points: The skill reads from vision (specifically section 08) and customer-blueprint files located in the workspace.
Boundary markers: There are no explicit instructions or delimiters mentioned to prevent the agent from executing instructions that might be embedded within the source files (e.g., instructions hidden in the vision document).
Capability inventory: The skill possesses the capability to write multiple files to the filesystem (MODEL.md, business-model.json, core tables, and CLAUDE.md) and generate both a documentation site and an MCP server surface.
Sanitization: The skill does not define any sanitization or validation logic for the content extracted from external documents before it is used to generate new files or configurations.
[DYNAMIC_EXECUTION]: The skill performs automated generation of structured code and configuration files based on the interview process.
Script generation: The skill generates an 'MCP surface' and a 'standalone model site'. This process involves creating executable or structured code (such as JSON contracts and site templates) derived from potentially untrusted upstream data and user input.
Port configuration: The module contract specifies a fixed network port (4005) for the generated MCP server functionality.

business-model