Trust verification

A public trust score any third party can check without authentication, and the fingerprint and status checks that sit behind it.

Trust Verification

Verify an agent's identity and trust score via the public Trust API. No authentication required for verification.

The endpoint is public. A counterparty can check an agent before dealing with it without an account, an API key, or any involvement from you, which is rather the point of publishing it. A score only you can read proves nothing to anybody else.

It scores the agent's own record rather than your company. Every agent starts at 50 and earns the rest, so a low score on a new agent means untested rather than untrustworthy.

vorim.verify(agentId)

const trust = await vorim.verify('agid_acme_a1b2c3d4');

console.log(trust.trust_score);    // 87
console.log(trust.status);         // 'active'
console.log(trust.owner.verified); // true — is the owning org verified
console.log(trust.active_scopes);  // ['agent:read', 'agent:execute']

typescript

Python

trust = vorim.verify("agid_acme_a1b2c3d4")

print(trust.trust_score)      # 87
print(trust.status)           # 'active'
print(trust.owner["verified"]) # True — is the owning org verified

# Async
async with AsyncVorim(api_key="agid_sk_live_...") as client:
    trust = await client.verify("agid_acme_a1b2c3d4")

python

Trust score factors (0-100):

Base scoreAll agents start at 50

StatusActive is the baseline; suspended -25; revoked or expired forces the score to 0

ReliabilityUp to +22, a Wilson lower bound on recency-weighted success (a few easy wins cannot buy full credit)

Recent failuresUp to -30, recency-weighted, so recent denials and errors weigh more than old ones

Age+2 (1d), +4 (7d), +7 (30d), +10 (90d)

Scope breadth-3 to -10 for a broad permission surface (more than 5 scopes), larger when elevated scopes are held

Need Help?

Book a demo for a walkthrough, or contact us for support. For enterprise needs, reach out at sales@vorim.ai.