The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns detected. The skill is designed for internal code quality checks and only interacts with local files in the .trellis directory.
[Indirect Prompt Injection] (LOW): The skill ingests data from local documentation files which constitutes an attack surface. However, the risk is negligible as the skill lacks network capabilities or sensitive file access, and its primary function is reporting and code modification based on local rules.
[Command Execution] (SAFE): The skill uses 'git status' which is a standard, low-risk command used to identify modified files for analysis.

check-frontend