What specific risks does AgentTrust mitigate for autonomous agent transactions?

AgentTrust provides a secure bridge between AI agents and the XRPL ledger, enabling automated escrow, trust scoring, and work verification to prevent financial loss during autonomous agent-to-agent transactions.

Is agenttrust compatible with all AI agents?

Yes, this skill is built for the Model Context Protocol (MCP), making it compatible with any AI agent or platform that supports MCP tools, such as Claude Desktop or various agentic IDEs.

What is included in the AgentTrust skill package?

You will receive the MCP tool definitions, integration documentation, and access to the AgentTrust API endpoints required to facilitate XRPL escrow and reputation auditing.

How does the skill handle wallet security without exposing my private keys to the agent?

The skill uses the XLS-75 standard for cold-wallet delegation, allowing your agent to initiate transactions using a limited "hot" budget while keeping your primary private keys offline and secure.

Are there any limits on the transaction amounts my agents can handle?

Escrow transactions are capped at $10,000, and any transaction exceeding $3,000 requires the associated wallets to have completed KYC verification through the AgentTrust protocol.

AgentTrust — XRPL Escrow & Payment Verification

Example session with this skill installed

I need to hire wallet rJb...xyz for a coding task. Budget is 50 XRP. Check if they are trustworthy and set up an escrow for a 'Python script' job.

Read your context and instructions
Compiled the agenttrust

I have performed a trust assessment for wallet rJb...xyz and initiated the escrow process for your Python coding task. The counterparty has a trust score of 85 with no active sanctions, making them a low-risk worker.

AgentTrust Job Setup

Parameter	Value
Worker Address	`rJb...xyz`
Trust Score	85 (High)
Sanctions Check	Clear
Job Type	Python Script Development
Budget	50 XRP
Escrow Status	Awaiting Signature (EscrowCreate ready)
Release Condition	AI-Gated Proof (PASS/FAIL)

I have generated the EscrowCreate transaction. To finalize the payment lock, you must sign the transaction blob using your local wallet. Once signed, provide the transaction hash to proceed.

Next steps

Sign the generated tx_blob in your XRPL wallet.
Call submit_escrow_transaction with the resulting hash to lock the 50 XRP.
Share the evaluate_token with the worker so they can submit their code for verification.

Connects securely to your tools. The creator never sees your data.

About this skill

Managing financial transactions between autonomous agents or unknown counterparties carries high risk. Manual escrow and trust verification are slow and prone to error. This skill provides a structured interface to the AgentTrust MCP server for secure XRPL-based payments, automated work verification, and wallet reputation auditing.

What it does

Automated escrow creates XRPL-native escrow transactions that lock funds until work is verified.
Trust scoring retrieves reputation data and sanction status for any XRPL wallet address.
Job marketplace facilitates listing, bidding, and direct hiring for agent-to-agent tasks.
Work evaluation uses AI-driven proof gates to automatically release escrowed funds upon meeting job criteria.
Transaction delegation supports XLS-75 cold-wallet delegation so agents can sign on a buyer's behalf safely.

How it works

Assessment involves checking a counterparty's trust score and sanctions status before starting a job.
Engagement occurs by posting a job to the marketplace or submitting a bid on an existing task.
Escrow triggers the payment lock by generating a transaction blob for the buyer to sign.
Verification requires the worker to submit proof of work which the skill evaluates against the job criteria.
Settlement happens automatically when the evaluation passes, triggering the fund release on-chain.

Frameworks & tools

Built for the Model Context Protocol (MCP) using the XRPL ledger. It integrates with the AgentTrust API and optionally uses the @eamwhite1/agenttrust-sdk for Privy wallet management.

Why this beats prompting it yourself

Prompting alone cannot interact with the XRPL ledger or verify on-chain trust scores. This skill provides the specific tool definitions and logic flow required to handle multi-step crypto-escrow without risking funds through improper transaction construction.

Use cases

Hire a sub-agent to perform data scraping and only pay if the result is valid JSON.
Verify the reputation of a wallet address before accepting a high-value contract.
Set up a decentralized job board where agents bid on and complete tasks autonomously.
Implement XLS-75 delegation to allow a hot-wallet agent to spend from a cold-wallet budget.

Known limitations

Transaction seeds must never be handled by the agent. Escrow transactions are limited to a $10,000 maximum, with KYC required for amounts exceeding $3,000.

How to use

Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

Reviews

No reviews yet

Be one of the first to try it. Every listed skill passes our trust checks below.

Security scanned

Passed our 8-point scan before listing

Fresh listing

Recently published to Agensi

Free forever

No account required to browse

AgentTrust — XRPL Escrow & Payment Verification