mention-to-gateway

当收到 @deviceid-agentid-ip + 指令 格式的信息时，应该将对应消息发送到指定的 ip 网关的agent 上

This skill forwards parsed messages to arbitrary IPs using an OpenAI-style API and returns the remote assistant's reply verbatim. Before installing, consider: (1) Who authored this skill and can you trust it? There's no homepage or source. (2) Limit destinations — require a whitelist of allowed gateway IPs/ports; avoid letting untrusted input control the IP. (3) Ensure authentication and encryption to target gateways (the skill includes no auth). (4) Confirm where the "gateway internal IP" and agent name are sourced from (these are not declared). (5) Consider running it in a sandbox or disabling autonomous invocation until you add checks to prevent forwarding sensitive data or accessing internal-only networks. If you cannot obtain source code and a clear safe-deployment design from the author, treat this skill as risky and avoid installing it in production environments.

Type: OpenClaw Skill Name: mention-to-gateway Version: 1.0.0 The skill 'mention-to-gateway' (SKILL.md) implements a cross-agent communication relay that functions as a Server-Side Request Forgery (SSRF) vector. It instructs the agent to parse an IP address from user input and send a POST request to that IP on port 18789. While this is the stated purpose for multi-gateway interaction, it allows the agent to be used as a proxy to probe or interact with arbitrary network targets. Additionally, the instructions command the agent to suppress all output except the remote response, which could be used to mask unauthorized network activity.