The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a testing fixture at test/test_fixture_regressions.py that utilizes subprocess.run to call the ansible-playbook command. This is a standard implementation for regression testing generated Ansible roles and is not triggered during regular skill operation.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided natural language to generate infrastructure code. It mitigates injection risks by following a deterministic workflow, referencing pre-defined security standards, and instructing the agent to mask sensitive information using the no_log attribute.
[SAFE]: The skill acts as a development aid, providing industry-standard templates for Ansible projects. While some templates include configurations such as host_key_checking = False in ansible.cfg, these are common defaults in development scaffolding and do not constitute malicious behavior.

ansible-generator