The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill utilizes railway status --json and command -v railway to interact with the environment. These are restricted to the intended purpose of checking infrastructure status.
[EXTERNAL_DOWNLOADS] (SAFE): The documentation suggests the user install the official @railway/cli via npm or brew. It does not perform any automated or hidden downloads.
[DATA_EXFILTRATION] (SAFE): No sensitive local files (e.g., SSH keys, env files) are accessed. Data retrieved from the CLI is intended for presentation to the user.
[PROMPT_INJECTION] (LOW): As the skill parses and presents output from an external tool (Railway CLI), there is a theoretical surface for indirect prompt injection if an attacker could control service or project names within the Railway account. This is a standard risk for skills processing external data.

railway-status