The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses python3 scripts/setup.py to perform profile creation, listing, and switching operations. This script is part of the local skill package and is used for intended functionality.
[DATA_EXPOSURE]: The skill reads and writes brand profile data to the user's home directory within ~/.claude-marketing/brands/. This access is restricted to the skill's own configuration and data subdirectories.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user-provided content, such as brand mission statements, voice samples, and competitor descriptions.
Ingestion points: User responses during interactive setup phases defined in SKILL.md.
Boundary markers: Absent; there are no specific instructions for the agent to use delimiters or ignore instructions within the ingested user content.
Capability inventory: The skill has the ability to execute a local Python script (scripts/setup.py) and perform file system write operations.
Sanitization: No specific validation or sanitization of the user-provided text or URLs is mentioned in the instructions.

brand-setup