Skip to content

For ERC-8004 and x402 builders

Reputation is only as good as the evidence behind it.

A 2026 study of ERC-8004 found most feedback is not tied to a verifiable interaction. TrustShell receipts say what was checked, and what was not.

See an agent’s recordTry Inspect →

Developer preview. No account, no key.

A real receipt · abridged

A claim an agent might make:

“The check workflow succeeded on commit 5d1c5e3f57e1, run 39619591025.”

Claims: 3 supported · 1 contradicted · 1 not checked
✗ CONTRADICTED commit 5d1c5e3f57e1
  The claim cites commit 5d1c5e3f57e1; the inspected run is on 392797a69b6a.
✓ SUPPORTED The check workflow succeeded
✓ SUPPORTED run 39619591025
exit 1

The run was on a different commit than the claim named. The check read that from GitHub’s own record. Run it yourself.

What worries people, and why it is justified

  • “On-chain reputation can be faked, so it tells me nothing.”

    An empirical study across Ethereum, BSC and Base found reputation values not comparable, feedback rarely tied to a verifiable interaction, and large shares of reviewers acting in coordinated, Sybil-like ways.[1]

    What TrustShell does. RepID is our engine’s score, written as ERC-8004 feedback on Base Sepolia, a test network. The scoring code is public, and each receipt says what was checked and what was not.

    What it does not do. Its tuned constants are not public, and nothing here makes reputation Sybil-proof. Tying feedback to evidence is next, and not built.

  • “My agent pays the wrong party, or more than it should.”

    An AI-linked wallet was talked into sending roughly $150,000 to $200,000 it was never meant to send.[2]

    What TrustShell does. The SDK refuses to sign an x402 payment with no cap, over the cap, or from a turn that may not pay.

    What it does not do. Test network only, no mainnet, and the cap comes from the calling code.

See it. Limit it. Keep it.

  • See it

    Check what your AI says against the record, and see what each checker said.

  • Limit it

    A spending cap set in code, not in a prompt. Test network only.

  • Keep it

    Your memory and profile stay on your machine, whichever model you use. Moving them to another machine as one signed file is in preview.

Make yours in three questions.

Your rules, your memory. No wallet to start.

Build your agent

Sources

These are reports we read, not measurements we made. Where a number matters, read the original before you rely on it.

  1. [1] Can Trustless Agents Be Trusted? An empirical study of ERC-8004 (arXiv 2606.26028). Data through May 2026 from Ethereum, BSC and Base. Version 1 and version 2 figures differ slightly.
  2. [2] OECD AI Incident Monitor: Grok / Bankr wallet drained by a Morse-code prompt (May 2026). The page values the loss at $150,000 to $200,000; headlines vary.