The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script to query the intelligence graph based on user-provided parameters.
Evidence: The Process section specifies executing intelligence-graph.py query-relevant with context dimensions provided by the user.
[DATA_EXPOSURE]: The skill accesses configuration and profile files located in a hidden application directory within the user's home folder.
Evidence: The skill reads from ~/.claude-marketing/brands/_active-brand.json and ~/.claude-marketing/brands/{slug}/profile.json to load brand context.
[PROMPT_INJECTION]: The skill processes untrusted user input and brand profile data to generate arguments for a command-line tool, presenting a surface for indirect prompt injection.
Ingestion points: User-provided query context and files in ~/.claude-marketing/.
Boundary markers: None identified in the instructions.
Capability inventory: Execution of the intelligence-graph.py script.
Sanitization: No explicit input validation or sanitization of the context dimensions is described.

recall