The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources and local files to generate its output, creating a surface for indirect instructions to influence the agent.
Ingestion points: The skill processes user-provided $ARGUMENTS and reads from several files: founder/facts.md, founder/product-brief.md, founder/persona-gen.md, and founder/validate-idea.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between data and potential commands within the ingested files.
Capability inventory: The skill is authorized to use Read and Edit tools within the founder/** directory scope.
Sanitization: The instructions do not include any validation, escaping, or filtering logic for the content retrieved from the input files before it is used to generate the interview script.

user-interviews