The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from multiple external project files to generate copy, which creates an indirect prompt injection surface. This is the primary function of the skill and is mitigated by restricted tool access.
Ingestion points: The skill reads files including facts.md, product-brief.md, persona-gen.md, pricing-strategy.md, competitor-matrix.md, and user-interviews.md from the founder/ directory as specified in the instructions.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present for the ingested file content.
Capability inventory: The skill is constrained by its frontmatter to only use Read and Edit tools within the founder/** directory.
Sanitization: No content sanitization or validation logic is defined for the input data.

landing-page