The Agent Skills Directory

[SAFE]: The skill's content is entirely instructional and focused on marketing strategy. There are no scripts, command execution, or network requests involved.
[DATA_EXPOSURE]: The skill instructions include a check for local project context files (e.g., .agents/product-marketing.md) to personalize recommendations. This is a standard context-awareness feature for AI agents and does not target sensitive user credentials or system files.
[PROMPT_INJECTION]: The instruction to respond in Russian by default is a functional preference for the agent's persona and does not attempt to bypass safety filters or ignore system instructions.

free-tools