The Agent Skills Directory

[SAFE]: The skill's instructions align perfectly with its stated purpose of brand strategy development. It uses standard file operations and interactive tools without any suspicious behavior.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from local project files, which is an inherent risk for AI agents.
Ingestion points: .design/branding/{brand}/BRIEF.md, .design/branding/{brand}/discover/INDEX.md, and mood-board-direction.md.
Boundary markers: No specific delimiters are used to wrap ingested content.
Capability inventory: The skill has access to Read, Write, Bash, Agent, WebFetch, and WebSearch tools.
Sanitization: No validation or sanitization is performed on the ingested text before it is processed by the agent or passed to the sub-agent.

brand-strategy