Railway CLI
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to manage cloud infrastructure, including deploying code (
railway up) and managing configuration (railway variables set). These commands interact with a well-known cloud provider. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could be influenced by an attacker, creating a vulnerability surface where the agent might interpret data as instructions.
- Ingestion points: The agent context receives untrusted data via
railway logsandrailway variables list(SKILL.md). - Boundary markers: None identified in the skill instructions to separate command output from agent instructions.
- Capability inventory: The skill has the capability to modify environment variables (
railway variables set) and trigger deployments (railway up), which could be abused if the agent is misled by malicious log content (SKILL.md). - Sanitization: No evidence of output sanitization or filtering of log data before it is processed by the agent.
Audit Metadata