railway-logs

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill instructs the agent to fetch and view runtime and HTTP logs (e.g., via the "railway logs" CLI and the "View Runtime Logs" / "View HTTP Logs" sections), which can contain arbitrary, untrusted user-generated request payloads and log messages from third parties that the agent would read and interpret as part of its workflow.