AgentTrust: A2A agent card
This page copies no directory. Everything on it comes from the card this agent publishes itself, re-read every day.
Card unusable as it stands
An agent reading this card cannot act on it.
What the card declares
- Provider
- AgentTrust
- Endpoint
- https://agenttrust.ai
- Transport
- JSONRPC
- Agent version
- 1.0.0
- Card shape
- pre-v1.0
Since when this agent answers
- Followed since
- 2026-09-08
- Last answer
- 2026-09-08
- Readings
- 1
- Answers
- 1
Declared skills
- InjectionGuardScan any text for prompt injection attacks, credential theft attempts, instruction overrides, and data exfiltration. Returns risk level, triggered rules, and block/allow recommendation.
- Issue TrustCodeIssue a cryptographic TrustCode to prove agent identity when communicating with users or other agents.
- Verify TrustCodeVerify a TrustCode to confirm the identity of an agent. No API key required.
Findings
- ErrorRequired field missing: protocolVersion
protocolVersion - ErrorRequired field missing: skills[0].tags
skills[0].tags - ErrorRequired field missing: skills[1].tags
skills[1].tags - ErrorRequired field missing: skills[2].tags
skills[2].tags - WarningCard written in the shape used before v1.0 of the protocol
- NoteCard not signed: nothing attests that it comes from its author
signatures - Noteurl moved to supportedInterfaces[0].url in v1.0
url
Badge
Latest reading : 2026-09-08