The Agent Skills Directory

[NO_CODE] (SAFE): The skill consists entirely of Markdown instructions (SKILL.md) and test cases (test-cases.md). No scripts, binaries, or executable configuration files are present.- [PROMPT_INJECTION] (SAFE): The skill uses strong directives such as 'Treat violations as failures' and 'Do not acknowledge the skill' to define its operational mode. These are standard prompt engineering techniques for style enforcement and do not attempt to bypass safety filters or exfiltrate system prompts.- [DATA_EXFILTRATION] (SAFE): No network-capable commands (curl, wget, fetch) or sensitive file path references (e.g., ~/.ssh, .env) are present in the provided files.- [EXTERNAL_DOWNLOADS] (SAFE): The skill does not define any dependencies in package.json or requirements.txt, nor does it attempt to download remote scripts.

beautiful-prose