MitID Human-in-the-Loop Safeguards
Deterministic execution protocols for pausing agent loops and escalating Danish citizen MitID app-swap approvals.
Installation
skills.sh / CLI
Install this skill directly into your AI coding agent or project.
npx skills add lordavocado/AgentAccess.dk --skill mitid-hitl-safeguardsAbout MitID Human-in-the-Loop Safeguards
Prevents autonomous agents from entering infinite retry loops, causing user account lockouts, or attempting automated bypasses when encountering Danish national identity gates (MitID, NemLog-in). Defines strict Human-in-the-Loop (HITL) handoff patterns, state persistence, and webhook polling limits.
SKILL.md Instructions
SKILL.mdSKILL.md
The procedural instructions executed step-by-step by the AI agent.
---
name: mitid-hitl-safeguards
description: Protocols for handling MitID authentication with mandatory human-in-the-loop safeguards.
metadata:
compliance: mitid-hitl
country: DK
---
# MitID Human-in-the-Loop (HITL) Safeguard Skill
Autonomous agents CANNOT solve MitID challenges, push notifications, or hardware authenticators.
## Safety Principles
1. **Zero Bypass Attempt**: Never simulate clicks on MitID authenticators or attempt credential stuffing.
2. **Immediate Pause**: The instant a MitID authentication challenge is generated, transition the agent state to `WAITING_FOR_HUMAN`.
3. **Clear Handoff Prompt**: Output a direct, unambiguous instruction to the human operator:
> "MitID confirmation requested. Please open the MitID app on your mobile device and swipe to approve action: [action description]. Agent paused."
4. **Timeout Cap**: Poll for completion status at maximum every 5 seconds, up to 180 seconds. If the human does not approve within 3 minutes, gracefully terminate with `AUTH_TIMED_OUT`.
Related Danish System
View systemMitID & MitID Erhverv
The Danish national digital identity infrastructure for citizen and business authentication.