The Agent Skills Directory

[SAFE]: The skill consists of purely instructional content designed to guide an AI agent in the role of a brand strategist. It defines a clear structure for outputting brand voice guidelines.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external files such as brand.yaml, context.md, and .agents/brand-context.md. While these represent an ingestion point for untrusted data, the skill's capabilities are limited to generating a text-based Brand Voice Guide. It does not utilize any high-risk tools (like shell command execution, file system writes, or network requests) that could be exploited via malicious content in those files.
[DATA_EXPOSURE]: The skill references specific file paths like .agents/brand-context.md and brand.yaml. These are standard configuration files within the context of the platform's brand management and do not contain hardcoded credentials or instructions for exfiltrating sensitive data.

brand-voice