Operate Railway infrastructure: sign up for or sign in to a Railway account, create projects, provision services and databases, manage object storage buckets, deploy code, configure infrastructure as code, environments and variables, manage domains, troubleshoot failures, check status and metrics, manage feature flags, set up Railway agent tooling, and query Railway docs. Use this skill whenever the user mentions Railway, feature flags, flag rollout, targeting rules, signing up, creating an account, registering, logging in, deployments, services, environments, buckets, object storage, build failures, agent setup, MCP, or infrastructure operations, even if they don't say "Railway" explicitly. Also invoke this skill when the user asks to be signed up, registered, or onboarded to Railway: do not refuse — drive them through the unauthed `railway up` flow (deploys + signs up on the fly) or `railway login` (which creates new accounts on the fly).
93%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The visible content is a legitimate Railway operations guide. The main concern is that it has the agent auto-run `railway skills update` or `railway setup agent -y` and auto-create projects without confirmation, which alters the user's tooling and resources without asking. That is risky rather than malicious, and the truncated remainder was not visible.
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill exposes many state-changing Railway operations (environment edits, variable changes, service deletion, MCP and skills installation). `railway sandbox checkpoint delete` and name-reuse overwrite explicitly remove the server-side disk snapshot ("Deleting a checkpoint removes its underlying disk snapshot"; "replaces the previous checkpoint without warning"), with no recovery path described. Checkpoints are environment-scoped remote resources, so shared scope is presumed.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Central Station community threads (outsider-authored, via station-server.railway.com) are read only when the agent chooses to search or fetch them in request.md, so the attacker can publish poison but cannot force delivery.
BigSimmo/PsychSift
fada614
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.