The Agent Skills Directory

[No Code] (SAFE): The skill is composed entirely of Markdown files (checklists and templates). There are no Python scripts, JavaScript files, or shell scripts included.
[Indirect Prompt Injection] (LOW): While the RFC workflow involves ingesting external research data into templates, the skill does not provide the agent with any capabilities (like file writes or network access) that could be exploited via malicious content in that data.
[Command Execution] (SAFE): The templates include example shell commands for a hypothetical project, which are intended as text documentation rather than instructions for the agent to execute on the local system.

rfc-creator