The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions define an attack surface for indirect prompt injection by requiring the agent to read several project-specific documentation files for context.
Ingestion points: The agent is directed to read .agents/product-marketing-context.md, .claude/product-marketing-context.md, POSITIONING.md, CONTENT_GUIDE.md, and STORY.md (documented in SKILL.md).
Boundary markers: The skill does not provide instructions to wrap the content of these files in delimiters or include 'ignore embedded instructions' warnings.
Capability inventory: Although the skill itself consists only of markdown instructions and references, it is intended for use in an environment where the agent has file-reading capabilities that could be subverted by instructions hidden in these documents.
Sanitization: There are no instructions for sanitizing, escaping, or validating the external content ingested from the specified project files.

copywriting