The Agent Skills Directory

[NO_CODE] (SAFE): The skill consists entirely of markdown instructions for the AI agent's behavior and does not include any scripts, binaries, or shell commands.
[DATA_EXPOSURE] (SAFE): The skill does not access sensitive files, environment variables, or hardcoded credentials. It only references a logical memory object 'ReactLearningProgress' for tracking user state.
[INDIRECT_PROMPT_INJECTION] (INFO): The skill is designed to process user input (topics and answers). While it lacks explicit boundary markers, its lack of external capabilities (network, file system, or command execution) prevents any significant security risk from untrusted user content.

react-study