InfoResearchPreprint
Agent Authenticator: Passkey-Grade, Hardware-Bound Authentication for AI Agents
- Published
- Record updated
Summary
The paper presents Agent Authenticator, a design giving AI agents passkey-grade authentication: per-service hardware-bound keys, no shared secrets, runtime-enforced origin binding, attestation of the execution environment, and human-signed scoped mandates. It deploys as a profile over existing mechanisms such as MCP authorization, OAuth token exchange and git/SSH, and produces a signed, hash-chained action record. The authors analyze it against prompt injection and same-host compromise, mapping it onto five documented incidents.
Topics
Related items
- MediumCVE-2026-130358: AdminNeo before 5.9.1 contains a missing authentication vulnerability in the ClaudeSqlPlugin, GeminiSqlPlugin, and…Similar attack · NVD/CVE Database
- HighGHSA-8vf2-hxg5-crqh: Kubeshark: MCP `start_kubeshark` argument injection via `pod_regex` → image redirect → cluster takeoverSimilar attack · GitHub Advisory Database
- MediumCVE-2026-126681: AWS Labs Timestream for InfluxDB MCP Server exposes API tokenSimilar attack · NVD/CVE Database
- HighCVE-2026-126681 - Improper restriction of intended endpoints in AWS Labs Timestream for InfluxDB MCP ServerSimilar attack · AWS Security Bulletins
- Medium'Sleeper Agent' Tactic Hides Payloads in Open-Weight AI ModelsSimilar attack · Dark Reading