The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for behavioral simulation. It contains no commands, script executions, file system operations, or network requests.- [INDIRECT_PROMPT_INJECTION]: The skill provides a framework for processing user-supplied character data (goals, beliefs, fears). While this represents a data ingestion surface, the skill lacks any capabilities (such as file writing, shell access, or external API calls) that would allow for exploitation via prompt injection. The risk is minimal as the instructions are contained within a creative writing context.

character-simulation