Agent Risk Scorecard - Read an Agent's On-Chain Risk
Turn an AI agent's on-chain history into a risk scorecard: settlement evidence, credit tier, recommended limit and rate, and a one-line verdict. Read-only, no account, no key.
Free
Works with the AI Agents you already use
Agent Risk Scorecard - Read an Agent's On-Chain Risk
Example session with this skill installed
An agent says it earns on-chain and wants a $5,000 limit. Its address is 0x.... What is its risk?
- Read your context and instructions
- Compiled the agent risk scorecard
A scorecard: verified settled payments, unique counterparties, defaults, address age, a tier from the published bands, and VERDICT: APPROVE tier B, limit $X, rate Y bps — with the rule that fired.
Connects securely to your tools. The creator never sees your data.
About this skill
A lender, insurer, or bonder asks how risky this agent is, and the agent's self-reported history is worthless. This free skill shows how to build a scorecard from settled on-chain facts: payments that actually cleared, payees and amounts that match, unique counterparties, defaults, and duplicate payment attempts. It gives explicit scoring bands, the three decision rules (a default caps the tier, a thin history is a reject, otherwise approve with terms from the score), a one-line verdict format that states which rule fired, and the honest limits of a scorecard. Read-only and unopinionated, it is the free view that leads to a signed, enforceable verdict.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Read-only and unenforceable. It describes verified history, not intent, and says nothing about off-chain obligations. For an enforceable decision, use a signed verdict.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
- Accounts
Base
Basescan
- Software
- Base network RPC accessA block explorer
Permissions
Allowed Hosts
Read-only public chain data. No funds move and no keys are needed.