risky-sign-in-triage

risky-sign-in-triage is an agent for coding agents from OpenAdminOS/OpenAdminOS. It costs 24 tokens per session (410 once invoked), scanned A, original, MIT.

A read-only review of recently risky users in Microsoft Entra, Microsoft's cloud identity service. It groups them by risk level, current state, risk details, and whether the issue has been processed.

In plain words
What is it for?
Use it to review risky-user records, classify recent identity threats, and produce cautious next-step guidance.
Why use it?
It helps administrators sort identity-risk alerts and understand which cases may need attention without changing user accounts.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/openadminos/openadminos/risky-sign-in-triage
Clone the repo
git clone --depth 1 https://github.com/OpenAdminOS/OpenAdminOS

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for risky-sign-in-triage

README.md
[![agentmods](https://agentmods.dev/badge/agents/openadminos/openadminos/risky-sign-in-triage.svg)](https://agentmods.dev/agents/openadminos/openadminos/risky-sign-in-triage)
Your own site
<a href="https://agentmods.dev/agents/openadminos/openadminos/risky-sign-in-triage"><img src="https://agentmods.dev/badge/agents/openadminos/openadminos/risky-sign-in-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 410 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00410
Opus 5 $0.00012 $0.00205
Sonnet 5 $0.00005 $0.00082
Haiku 4.5 $0.00002 $0.00041

Measured 4d ago against content hash 74fafae1a663, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

risky-sign-in-triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/gitbook/generated/agents/risky-sign-in-triage.md · 59 lines

What it actually says

Risky user triage

Classifies recent Entra risky users by risk level, state, detail, and processing status with conservative next-step guidance.

Classification

Field Value
Agent ID risky-sign-in-triage
Version 1.1.0
Mode read
Tier agent
Category policies
Required Entra tier p2
Preferred model llama3.1:8b
Minimum app version 0.1.0
Author OpenAdminOS · verified
Last changed 2026-05-29 · 3a69fc6

Execution

This agent runs through the host-side Agent Template interpreter.

Tenant Data Access

Step Graph call Scopes
Load risky users GET /identityProtection/riskyUsers IdentityRiskyUser.Read.All

Graph Scopes

  • IdentityRiskyUser.Read.All

Write Behavior

This is a read-only agent. It does not declare write operations.

LLM Use

Step Settings
Classify this risky user temperature 0.1 · max tokens 150
Roll up triage results temperature 0.2 · max tokens 420

Settings

No user-configurable settings are declared.

Source

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 59 lines · 24 tokens per session scan A 74fafae1a663

Subscribe to this mod's changes

risky-sign-in-triage is an agent published in the GitHub repository OpenAdminOS/OpenAdminOS (54 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 410 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.