The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands using the railway CLI for project lifecycle management, such as railway init, railway link, and railway add. It also leverages npm and npx for project scaffolding and package management.
[EXTERNAL_DOWNLOADS]: The skill directs the installation of the official Railway CLI (@railway/cli) from the npm registry and utilizes well-known scaffolding tools like vite and astro. These resources are consistent with the skill's infrastructure automation goals and originate from trusted registries.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied project names and analyzes local codebase files (e.g., package.json, requirements.txt, go.mod, Cargo.toml) to automate service configuration. Ingestion points: User-provided service names and project file contents analyzed in SKILL.md and railpack.md. Boundary markers: Absent. Capability inventory: Shell command execution via Railway CLI and npm tools in SKILL.md. Sanitization: Absent. While these surfaces could theoretically be targeted by malicious project files, the risk is inherent to the skill's primary function of infrastructure scaffolding.

railway-new