The Agent Skills Directory

[SAFE]: The skill provides structured instructions for a personal branding strategist role. It contains no executable code, remote script downloads, or attempts to bypass safety filters. All instructions are focused on providing a branding framework and gathering user information for strategy development.
[INDIRECT_PROMPT_INJECTION]: The skill references a local file .agents/brand-context.md as an ingestion point for context. While this file represents external data, the skill has a minimal attack surface because it lacks capabilities such as shell execution, file writing, or network operations. The risk of data-driven exploitation is negligible in this context.
Ingestion points: Reads .agents/brand-context.md (SKILL.md).
Boundary markers: None present; the skill assumes the content is valid brand context.
Capability inventory: No subprocess calls, network operations, or file-write capabilities were found in the skill.
Sanitization: No specific sanitization or validation of the input file content is implemented.

personal-brand