The Agent Skills Directory

[SAFE]: The skill consists exclusively of instructional Markdown and supporting data files (YAML, JSON). No executable scripts, binary files, or malicious command patterns were identified. The skill is designed to guide an agent through a conversational 'Wizard' workflow to help users refine ideas.
[DATA_EXPOSURE]: The skill is configured to read and write project-related 'idea' records within specific project directories (e.g., .lev/pm/ideas/). It does not attempt to access sensitive system paths, credentials, or environment variables outside of its declared project scope.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted user input (idea topics). However, it mitigates potential risks by using clear structural boundaries and templates, and it lacks high-risk capabilities like arbitrary shell execution or network exfiltration that could be exploited via indirect injection.

idea