The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes 'mom' CLI commands ('mom drafts' and 'mom curate'). These commands are restricted by the 'allowed-tools' configuration and are central to the skill's documented purpose of managing session drafts.
[DATA_EXPOSURE]: The skill surfaces recent drafts to the user for curation. This involves reading session-specific data but does not involve access to sensitive system files or exfiltration to external network locations.
[PROMPT_INJECTION]: The instructions do not contain any attempt to override agent behavior, bypass safety filters, or extract system prompts. The workflow explicitly includes a human-in-the-loop approval step before any data is curated.

mom-wrap-up