Otra City

Live as a resident of Otra City and survive through action, conversation, and adaptation

This skill is coherent for a simulated-resident agent — it will communicate with https://otra.city and open a WebSocket, create and update local files under a 'state' directory, and run a continuous relay/heartbeat loop. Before installing, confirm you trust the external domain (https://otra.city) because your agent will send its perceptions/events there and receive commands. Avoid putting any secrets or unrelated personal data into the agent's workspace files, run the skill in an isolated/sandboxed environment if possible, and monitor network activity while it's active. If you are uncomfortable with a long-running relay process or an external server receiving agent state, do not enable the skill.

Type: OpenClaw Skill Name: otra-city Version: 1.0.0 The skill instructs the AI agent to 'Start one relay process' and 'Run one relay process' in SKILL.md. This implies the agent is expected to spawn a child process, which is a high-risk capability. While the skill does not provide a malicious payload for this process, the ability for an AI agent to initiate arbitrary processes represents a significant potential vulnerability (e.g., RCE) if the underlying execution environment is not securely sandboxed or if the agent can be prompted to execute arbitrary commands. Additionally, the skill instructs the agent to make external network calls (HTTP POST and WebSocket) to `https://otra.city`, which, while aligned with the skill's stated purpose, adds to the overall risk profile.