The Agent Skills Directory

NO_CODE (SAFE): The skill consists entirely of Markdown instructions (SKILL.md and assets/operators.md) and does not include any executable scripts, binary files, or package managers (e.g., package.json or requirements.txt).\n- DATA_EXFILTRATION (SAFE): No network requests (curl, wget, fetch) or sensitive file path access (e.g., ~/.ssh, .env) were detected in the files.\n- COMMAND_EXECUTION (SAFE): There are no shell commands or subprocess invocations present in the instructions.\n- PROMPT_INJECTION (SAFE): The content focuses on creative brainstorming workflows. It does not attempt to bypass safety filters, extract system prompts, or override agent constraints in an adversarial manner.\n- EXTERNAL_DOWNLOADS (SAFE): No external URLs or remote code execution patterns were found.

creativity