The Agent Skills Directory

[SAFE]: The skill is a comprehensive knowledge base and instructional framework for marketing psychology. It does not include any executable code, scripts, or remote dependencies.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is instructed to read brand context files from potentially untrusted sources in the './brands/' directory. However, this risk is assessed as safe because the skill has no actionable tools, subprocess capabilities, or network access that could be exploited by malicious instructions. Ingestion points: Brand identity and positioning files such as './brands/{brand-slug}/brand-context.md'. Boundary markers: No explicit separators or instructions to ignore embedded commands are present in the provided files. Capability inventory: The skill has no access to dangerous tools (no shell execution, no network operations, no file-writing). Sanitization: The content read from the context files is used directly for grounding and is not filtered or sanitized.

marketing-psychology