← Back to Skills Marketplace
Openclaw
by
nicholasraimbault
· GitHub ↗
· v0.5.2
· MIT-0
397
Downloads
0
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install skytale
Description
The trust layer for AI agents — encrypted channels, identity, audit, attestations, trust circles, key rotation, and federation. MLS protocol (RFC 9420).
Usage Guidance
This skill appears to do what it says: provide an MLS-based trust layer via the Skytale Python SDK. Before installing, confirm you trust the skytale.sh service and the skytale-sdk package on PyPI (verify package name, maintainer, and release history). Treat SKYTALE_API_KEY as highly sensitive: give it least privilege, store it securely, and rotate/revoke it if you suspect misuse. Review the skytale-sdk code (or your security team's vetting) if your environment requires stricter supply-chain assurance, and avoid placing API keys in shared config files (examples/openclaw-config.json includes keys in env blocks — do not commit real keys to source control).
Capability Analysis
Type: OpenClaw Skill
Name: skytale
Version: 0.5.2
The Skytale skill bundle provides a suite of tools for end-to-end encrypted communication between AI agents using the MLS protocol (RFC 9420). The bundle includes a standard setup script for installing the 'skytale-sdk' via pip and provides clear, security-conscious instructions in SKILL.md for managing encrypted channels, identities, and audit logs. No evidence of malicious intent, unauthorized data exfiltration, or suspicious obfuscation was found; the required network access and API key usage are consistent with the stated purpose of providing a secure messaging relay (skytale.sh).
Capability Assessment
Purpose & Capability
Name/description (Skytale/MLS trust layer) match the requested items: python as runtime and a SKYTALE_API_KEY. Examples and SKILL.md show using skytale-sdk, MCP server integration, identity, encrypted channels, audit logs and federation, which are all consistent with the stated purpose.
Instruction Scope
SKILL.md limits runtime actions to installing/using the skytale-sdk, configuring an MCP entry, and calling SDK/MCP functions to create/join channels, send/receive messages, manage keys, and record encrypted audit logs. It does require the agent to hold and use the SKYTALE_API_KEY (sensitive) and the examples add SKYTALE_IDENTITY in env; users should understand the skill enables networked operations to Skytale servers and will transmit user-supplied messages and state to that service.
Install Mechanism
No packaged install spec in the registry; the skill is instruction-first and includes a setup.sh that invokes pip to install skytale-sdk[mcp]. Using pip for a named SDK is typical; this is a moderate-risk operation (third-party package install) but consistent with the skill's needs. No downloads from arbitrary URLs or obfuscated installers are present.
Credentials
The skill requests a single primary credential (SKYTALE_API_KEY), and examples also reference SKYTALE_IDENTITY for MCP runtime. The number of env vars is proportional to the integration, but the SKYTALE_API_KEY is powerful — it grants access to the Skytale API and should be treated as a sensitive secret with least-privilege and rotation policies.
Persistence & Privilege
The skill is not always-enabled (always: false), is user-invocable, and does not request system-wide configuration changes. Its setup script installs a Python package but does not modify other skills or agent-wide configs beyond instructions to add an MCP server entry. No excessive persistence or privilege escalation is requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install skytale - After installation, invoke the skill by name or use
/skytale - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.5.2
- Updated the skill description to: "The trust layer for AI agents — encrypted channels, identity, audit, attestations, trust circles, key rotation, and federation. MLS protocol (RFC 9420)."
- No functional changes; documentation and description update only.
v0.5.1
Add encrypted shared context, key rotation, encrypted audit logs, cross-org federation, agent visibility tiers
v0.5.0
Update for SDK 0.5.0: fix MCP tool list, add identity/audit/attestations/trust/registry features
v0.1.0
Initial release: E2E encrypted messaging channels for AI agents via MCP tools
Metadata
Frequently Asked Questions
What is Openclaw?
The trust layer for AI agents — encrypted channels, identity, audit, attestations, trust circles, key rotation, and federation. MLS protocol (RFC 9420). It is an AI Agent Skill for Claude Code / OpenClaw, with 397 downloads so far.
How do I install Openclaw?
Run "/install skytale" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openclaw free?
Yes, Openclaw is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Openclaw support?
Openclaw is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux).
Who created Openclaw?
It is built and maintained by nicholasraimbault (@nicholasraimbault); the current version is v0.5.2.
More Skills