The Agent Skills Directory

[SAFE]: The skill is a purely instruction-based prompt for an AI agent. It does not contain any executable scripts, shell commands, or external package dependencies. Its functionality is limited to text generation based on the provided research papers (Chi et al., etc.).- [DATA_EXPOSURE]: The skill does not request access to the file system, environment variables, or sensitive user directories. There are no hardcoded credentials or API keys present in the SKILL.md file.- [REMOTE_CODE_EXECUTION]: No network operations (curl, wget) or remote script execution patterns were detected. The skill does not download or execute any external code.- [PROMPT_INJECTION]: The internal instructions for the AI agent are focused on educational design. While they include 'CRITICAL PRINCIPLES', these are used to guide the model's educational output quality and do not attempt to bypass safety filters, extract system prompts, or override agent constraints.- [INDIRECT_PROMPT_INJECTION]: The skill ingests 'learning_material' provided by the user. While there are no explicit delimiters or sanitization routines mentioned in the prompt, the skill has no access to sensitive tools (network, filesystem, or shell execution), which mitigates the risk of indirect injection to a negligible level.

self-explanation-prompt-designer