The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a local script ../schemas/scripts/schema.py to materialize directory skeletons and audit project layouts. This is a legitimate use of a project-local utility for automation.
[PROMPT_INJECTION]: The skill instructions are focused on organizational best practices and documentation maintenance. There are no attempts to bypass safety filters, extract system prompts, or override agent behavior.
[DATA_EXFILTRATION]: The skill operates locally on project files. No network operations or attempts to access sensitive system-level credentials (like SSH keys or AWS configs) were detected.

ag-dir