The Agent Skills Directory

[DATA_EXFILTRATION]: The skill accesses files within the ~/.claude-marketing/ directory to retrieve brand profiles, guidelines, and standard operating procedures. This file access is restricted to the application's own configuration data and is required to fulfill the user's request for brand-aligned content strategy.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by incorporating external data into its reasoning process.
Ingestion points: Reads from ~/.claude-marketing/brands/{slug}/profile.json, ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json, and the ~/.claude-marketing/sops/ directory.
Boundary markers: Absent. No specific delimiters or safety instructions are used when interpolating these files into the agent's context.
Capability inventory: The skill uses secondary agents (content-creator and seo-specialist) to generate complex content strategy and outlines based on the loaded data.
Sanitization: Absent. Data from these local profile files is applied directly to the content generation logic to determine brand voice and compliance.

content-brief