The Agent Skills Directory

[DATA_EXPOSURE]: The skill reads and writes sensitive legal information, including parties, conflict check results, and risk assessments. These operations are restricted to the application-specific path ~/.claude/plugins/config/claude-for-legal/, which is consistent with its intended use as a legal matter management tool.
[COMMAND_EXECUTION]: The instructions direct the agent to perform file system operations such as directory creation and file writing. These actions are limited to the designated workspace and do not involve system-level privileges or arbitrary command execution.
[PROMPT_INJECTION]: The skill processes user-supplied data to populate legal document templates. While this creates a potential surface for indirect prompt injection, the workflow mitigates this by requiring a manual confirmation step where the user reviews the exact output before any files are written to the disk.

matter-intake