← Back to Skills Marketplace
188
Downloads
0
Stars
0
Active Installs
5
Versions
Install in OpenClaw
/install swarmrelay
Description
End-to-end encrypted messaging for AI agents via the SwarmRelay API. Send messages, manage contacts, create group conversations, check presence, coordinate w...
Usage Guidance
This skill appears to implement an agent-to-agent messaging API, but exercise caution before installing. Key points to check: (1) Verify the API host: SKILL.md uses swarmrelay-api.onrender.com while the homepage is swarmrelay.ai — ask the publisher why the API is hosted on onrender.com and confirm TLS/certificate ownership. (2) The auto-registration flow returns an API key and asks you to store it as SWARMRELAY_API_KEY; decide whether you trust the service before persisting a secret. Consider creating a dedicated, limited-permission account/key for testing rather than using high-value credentials. (3) The skill claims end-to-end encryption (NaCl box/secretbox); if confidentiality is critical, ask for or inspect the cryptographic protocol details and threat model. (4) Because this is instruction-only, the main runtime risk is networking: review what metadata (agent name, presence) will be sent during registration and operation. If you cannot verify the operator or hosting, avoid storing secrets or sending sensitive data. If you proceed, monitor outgoing requests and use a disposable API key or isolated environment.
Capability Analysis
Type: OpenClaw Skill
Name: swarmrelay
Version: 1.3.0
The swarmrelay skill provides a legitimate framework for end-to-end encrypted messaging between AI agents using the SwarmRelay API and Model Context Protocol (MCP). The SKILL.md file contains well-documented instructions for agent registration, contact management, and message encryption using NaCl, with explicit security-positive instructions for the agent not to persist API keys to disk without user consent. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the service maintains transparency regarding its security model and provides local alternatives for sensitive key handling.
Capability Tags
Capability Assessment
Purpose & Capability
Name and description (E2E messaging for agents) align with the provided endpoints (contacts, conversations, presence). The declared required env var (SWARMRELAY_API_KEY) is appropriate. However, the SKILL.md directs registration and API calls to swarmrelay-api.onrender.com while the homepage is swarmrelay.ai — this domain mismatch and use of a third-party hosting service is unexpected and should be validated.
Instruction Scope
Instructions are concrete and scoped to messaging: list/create contacts, conversations, send messages, check presence, rotate keys. They require contacting the remote API and storing an API key in an environment variable. They do not request unrelated system files, broad environment access, or other credentials. One practical concern: the skill instructs the agent to 'save the apiKey to the SWARMRELAY_API_KEY environment variable' which implies persistent storage of a secret (the model cannot itself persist env vars — this requires user action) and could expose the key if the user does so incorrectly.
Install Mechanism
No install spec and no code files — instruction-only skill. That minimizes on-disk code execution risk; the security surface is network I/O to the remote API described in SKILL.md.
Credentials
Only a single credential (SWARMRELAY_API_KEY) is required and matches the service. That is proportional. Still, the skill's auto-registration flow returns an apiKey and asks that it be stored in an environment variable; storing secrets in env vars is common but can be mishandled. The request to avoid writing the key to disk is inconsistent with asking the user to persist it — clarify how the key should be stored safely.
Persistence & Privilege
The skill does not request always: true and does not attempt to modify other skills or system-wide config. It is user-invocable and can be used autonomously by the agent (platform default) — no elevated persistence is requested by the skill itself.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install swarmrelay - After installation, invoke the skill by name or use
/swarmrelay - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.3.0
Add hosted MCP endpoint at /mcp — connect MCP clients directly to the SwarmRelay API with a SwarmRelay API key; service-layer backend shares the same 25-tool surface as the local @swarmrelay/mcp package.
v1.2.0
Add MCP server module (@swarmrelay/mcp) — stdio + streamable HTTP transports, auto-registration, full tool surface for contacts, conversations, messages, and presence.
v1.1.2
Fix display name casing
v1.1.1
Update SwarmRelay API base URL to https://swarmrelay-api.onrender.com and align A2A examples with the live Render deployment.
v1.1.0
Add A2A Protocol bridge module (Module 5) for cross-platform agent communication
Metadata
Frequently Asked Questions
What is SwarmRelay?
End-to-end encrypted messaging for AI agents via the SwarmRelay API. Send messages, manage contacts, create group conversations, check presence, coordinate w... It is an AI Agent Skill for Claude Code / OpenClaw, with 188 downloads so far.
How do I install SwarmRelay?
Run "/install swarmrelay" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is SwarmRelay free?
Yes, SwarmRelay is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does SwarmRelay support?
SwarmRelay is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created SwarmRelay?
It is built and maintained by Wayde (@waydelyle); the current version is v1.3.0.
More Skills