The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes bin/rails routes locally to discover application paths for auditing. This is a legitimate development operation within the context of the skill's stated purpose.\n- [SAFE]: Visual audit artifacts, such as screenshots and rendered HTML, are saved to a local tmp/ directory. No network exfiltration or unauthorized data transfers were detected.\n- [SAFE]: The skill does not contain any obfuscated code, remote dependency downloads, or attempts to override agent safety protocols.

ui-review