The Agent Skills Directory

[SAFE]: No security issues detected. The skill operates as a set of logical instructions for the AI agent to follow during a conversation.
[DATA_EXPOSURE]: The skill references a local configuration file path ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md to load user preferences and existing outlines. This is a localized path within the expected environment for this type of legal-tech plugin and does not represent an exfiltration risk.
[PROMPT_INJECTION]: The skill includes robust internal safety guidelines (e.g., the 'don't write it for me' rule) that explicitly prevent the agent from bypassing its intended educational purpose, which serves as a defense against user attempts to misuse the tool.

outline-builder