InterAI Risk Oracle

Pre-execution verification for proposed autonomous actions. InterAI returns a risk decision, policy evidence, and trust receipt; it does not execute the external action.

Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-09-29T22:46:26Z, first seen 2026-09-16T13:21:30Z). Not self-submitted, not cached from a directory.

Measured card surface

field	value
A2A endpoint	`—`
card source	https://api.interailabs.dev/.well-known/agent-card.json
protocolVersion	—
agent version	0.1.3-beta.1
preferredTransport	—
provider	InterAI
skills published	2
card hash (canonical)	`afc9e6eed5e8ef22`

Skills (from card)

skill	description
Verify an autonomous action	Evaluate one proposed action before execution and return the InterAI decision, policy evidence, economic usage, and trust receipt. This skill never executes the action.
Verify a batch of actions	Evaluate a bounded batch of proposed actions before execution and return one result and trust receipt per item. This skill never executes the actions.

Card-drift history

Watching this agent since 2026-09-16T13:21:30Z. Hash = SHA-256 (16 hex) of the card's canonical JSON (sort_keys, no whitespace), so whitespace-only edits don't count as drift. Feed: api/a2a-drift.json.

when (UTC)	what	version	skills	hash was	hash now
2026-09-16T16:41:45Z	changed	0.1.3-beta→0.1.3-beta.1	2→2	`d59c43dec0`	`afc9e6eed5`

Same host, MCP side

Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.

MCP endpoint	grade	MCP OK	auth
https://api.interailabs.dev/mcp	A	✓	open

Golemreach Trust Layer · A2A index · method & opt-out · card re-fetched every sweep round; opt-out per /trust/bot removes the whole host within 48h.