The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and does not include any executable scripts, binary files, or configuration that would trigger automated code execution.
[SAFE]: The instructions explicitly mandate a "read-only" approach, repeatedly stating that the agent must not edit, move, or delete any data during the audit process.
[DATA_EXPOSURE]: While the skill instructs the agent to access potentially sensitive platforms like Slack, Jira, and internal GitHub repositories, it does so using the agent's existing authenticated environment and does not attempt to send this data to any external or unauthorized third-party domains.

ssot-check