The Agent Skills Directory

[PROMPT_INJECTION]: The skill operates by ingesting data from an external file to generate structured documentation and executable test code, which presents an indirect prompt injection surface. Ingestion points: The skill requires an input file, specifically usecases.md, as defined in the parameters. Boundary markers: There are no explicit instructions or delimiters used to ensure the agent ignores or sanitizes potential commands embedded within the input file. Capability inventory: The skill is designed to write multiple file types (Markdown and TypeScript) to the output/pm/ directory on the local file system. Sanitization: Input content is interpolated into templates without validation or escaping logic.

test-planner