Agntor Skill for OpenClaw
The Agntor Skill gives your OpenClaw agent a trust layer — prompt injection guard, PII redaction, identity verification, and escrow payments. Once installed, your agent will automatically guard inputs, redact secrets, and verify other agents before transacting.Install
~/.openclaw/openclaw.json:
What It Does
Once installed, the skill teaches your OpenClaw agent to:Guard Every Input
Before processing any message from an external agent or untrusted source, the agent runsguard_input to detect prompt injection. Blocked messages are refused with an explanation.
Redact Every Output
Before sending any response that may contain sensitive data, the agent runsredact_output to strip private keys, API tokens, SSNs, and other PII.
Verify Other Agents
When interacting with external agents (via OpenClaw’ssessions_send), the agent checks their trust score first:
Escrow Payments
Never sends funds directly. Creates escrow that releases on verified task completion:Tools Reference
MCP Server
The skill connects to Agntor via the MCP server. You can also use it standalone in any MCP client:Why OpenClaw + Agntor
OpenClaw’ssessions_send lets agents message each other. But when Agent A messages Agent B, neither knows if the other is trustworthy. Agntor solves this:
- Before
sessions_send: verify the target agent’s trust score - During execution: guard all inputs for injection, redact all outputs for leaks
- For payments: escrow funds so work is verified before release
- Emergency: kill switch to disable a compromised agent instantly