ERC-8004 Trustless Agents skill
Resolve ERC-8004 Trustless Agents
Teams need reliable agent identity and reputation context across chains. This skill guides Claude, Codex, and Claude Code through ERC-8004 resolution and AgentCard scaffolding.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "ERC-8004 Trustless Agents skill" from https://skillstore.io/skills/internet-court-trustless-agents.md and its manifest at https://skillstore.io/api/skills/internet-court-trustless-agents/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "ERC-8004 Trustless Agents skill". Resolve agent ID 0 on Base.
Expected outcome:
The assistant returns a short owner and AgentCard summary, then flags any missing trust or endpoint details.
Using "ERC-8004 Trustless Agents skill". Draft an AgentCard for a support agent with A2A and MCP services.
Expected outcome:
The assistant describes the required card fields in plain language and provides a host-ready structure without submitting a transaction.
Using "ERC-8004 Trustless Agents skill". List ERC-8004 registry addresses.
Expected outcome:
The assistant names the Identity and Reputation registries, supported chains, and draft caveats from the skill instructions.
Security Audit
Low RiskAll eight static findings are false positives caused by Markdown inline-code delimiters and a documented well-known URL path. The documented public-RPC fallback may expose query metadata to third-party providers.
Confirmed security concerns (1)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/internet-court-trustless-agents/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/internet-court-trustless-agents?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/internet-court-trustless-agents?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/internet-court-trustless-agents/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/internet-court-trustless-agents.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA ยท BibTeX ยท CFF)
APA citation
internet-court. (2026). ERC-8004 Trustless Agents skill security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/internet-court-trustless-agents/audits/2BibTeX citation
@techreport{internet-court-internet-court-trustless-agents-2026,
author = {internet-court},
title = {ERC-8004 Trustless Agents skill security audit report (audit version 2)},
institution = {Skillstore},
year = {2026},
number = {2},
url = {https://skillstore.io/skills/internet-court-trustless-agents/audits/2},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ERC-8004 Trustless Agents skill security audit report (audit version 2)"
version: "unspecified"
type: report
authors:
- name: "internet-court"
date-released: "2026-07-19"
url: "https://skillstore.io/skills/internet-court-trustless-agents/audits/2"
identifiers:
- type: other
value: "skillstore:internet-court-trustless-agents:audit:2"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Prepare Agent Registration
Create a registration card before publishing an on-chain agent identity.
Research Agent Identity
Inspect ERC-8004 registry concepts and compare agent identity data across chains.
Check Integration Metadata
Resolve known agent IDs and review AgentCard service metadata before integration.
Try These Prompts
Use the ERC-8004 skill to resolve agent ID 0 on Base. Summarize the owner, AgentCard location, and trust details.
List the canonical ERC-8004 Identity and Reputation registry addresses. Include supported chains and note any draft status.
Create a registration-v1 AgentCard plan for an agent named <name>. Include services, supported trust models, and x402 support.
Evaluate whether my agent metadata is ready for ERC-8004 registration. Check endpoint completeness, trust model coverage, and x402 payment notes.
Best Practices
- Verify registry addresses against the current ERC-8004 reference before production use.
- Host AgentCards at stable HTTPS or IPFS locations before registration.
- Treat write operations as out of scope until final ABIs are published.
Avoid
- Do not submit identity or reputation transactions from this skill alone.
- Do not assume draft ERC-8004 fields are final.
- Do not publish AgentCards with missing service endpoints or trust model details.
Frequently Asked Questions
What is ERC-8004?
Does this skill register agents on-chain?
Which tools can use this skill?
Does it require ChainGPT credits?
Can it resolve IPFS or data token URIs?
Is BASE_RPC_URL required?
Developer Details
Author
internet-courtLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Repository
https://github.com/internet-court/internet-court-skill/tree/main/vendored/chaingpt/trustless-agentsRef
3f6e026a3363e0954ede7bef0cfe88d4475de137
Maintenance freshness
7/18/2026
Usage
1 downloads ยท 0 views
File structure
๐ SKILL.md