The Agent Skills Directory

[SAFE]: The content is entirely instructional and does not include any executable scripts, shell commands, or remote dependencies.
[DATA_EXPOSURE]: The skill incorporates best practices for data security by instructing the agent never to persist sensitive information such as API keys, tokens, or personal identifiers. It also recommends using a .gitignore file for the memory directory to prevent accidental credential leakage to version control.
[PROMPT_INJECTION]: While the skill establishes a mechanism for the agent to adapt its behavior based on user feedback, it focuses on professional development conventions and architectural rationale rather than instructions to bypass safety protocols or override core agent constraints.

memory-management