The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script named journey-engine.py using the simulate argument to perform Monte Carlo simulations. This represents the execution of code external to the skill's own instructions.
[COMMAND_EXECUTION]: The process involves reading from sensitive file paths in the user's home directory, specifically ~/.claude-marketing/brands/ and ~/.claude-marketing/sops/. Accessing files outside the project root can lead to the exposure of sensitive brand and configuration data.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from untrusted local files.
Ingestion points: Files located at ~/.claude-marketing/brands/_active-brand.json, ~/.claude-marketing/brands/{slug}/profile.json, and ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json are read and their content is applied to the agent's context.
Boundary markers: None are specified to delimit the ingested content or warn the agent against following instructions embedded within these files.
Capability inventory: The skill has the capability to execute shell commands (journey-engine.py).
Sanitization: No sanitization or validation of the ingested JSON data is described before it is used to inform journey design logic.

journey-design