The Agent Skills Directory

[SAFE]: The skill functions as a domain-specific knowledge base for marketing and behavioral science, providing legitimate educational and strategic content.
[DATA_EXPOSURE]: The instructions direct the agent to read specific local files (e.g., product-marketing.md) to adapt its recommendations. This is a targeted search for marketing context and does not involve accessing sensitive system files, credentials, or private user data.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection via the ingestion of project-specific marketing files.
Ingestion points: Reads .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md (documented in SKILL.md).
Boundary markers: None identified; the skill does not explicitly warn the agent to ignore instructions embedded within these files.
Capability inventory: The skill utilizes no dangerous tools, network operations, file-writing commands, or code execution capabilities.
Sanitization: No sanitization or validation of the file content is performed before processing.

marketing-psychology