threat-triage

threat-triage is a command for Claude Code from WYRE-AI/msp-claude-plugins. It costs 15 tokens per session (1,260 once invoked), scanned A, original, Apache-2.0.

A command for reviewing recent email threats found by Abnormal Security, an email security service, and sorting them by urgency and attack type.

In plain words
What is it for?
Filtering threats by severity, type, status, and date, then producing a prioritized list with key details and recommended actions.
Why use it?
It puts the most serious and risky threats first, reducing the time needed to decide which messages require attention.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the abnormal-security plugin — 3 skills, 3 commands, 2 agents shipped together

Good fit Filtering threats by severity, type, status, and date, then producing a prioritized list with key details and recommended actions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/wyre-ai/msp-claude-plugins/threat-triage
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.

Clone the repo
git clone --depth 1 https://github.com/WYRE-AI/msp-claude-plugins

Made for: Claude Code.

Or install abnormal-security, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 2 agents.

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 threat-triage

README.md
[![agentmods](https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/threat-triage/github.svg)](https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/threat-triage)
Your own site
<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/threat-triage"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/threat-triage/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for threat-triage

Your own site · 80×15
<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/threat-triage"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/threat-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,260 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00015 $0.01260
Opus 5.5 $0.00006 $0.00504
Sonnet 5.5 $0.00003 $0.00252
Haiku 4.5 $0.00002 $0.00126

Measured 1mo ago against content hash 4298a8e92a81, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

threat-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 1mo 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.

msp-claude-plugins/abnormal/abnormal-security/commands/threat-triage.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threat Triage

Triage recent email threats detected by Abnormal Security, prioritized by severity and attack type.

Prerequisites

  • Valid Abnormal Security API token configured (ABNORMAL_API_TOKEN)
  • API token must have threat detection read permissions

Steps

  1. Build search filter

    • Parse all provided arguments
    • Map text values to API codes (type, severity, status)
    • Construct OData filter expression
  2. Fetch recent threats

    GET /v1/threats?filter=...&pageSize=...
    Authorization: Bearer <token>
    
  3. Sort by priority

    • Critical severity first, then High, Medium, Low
    • Within same severity, BEC and supply chain threats first
  4. Format triage report

    • Display threat list with key details
    • Include severity indicators and recommended actions

Parameters

Parameter Type Required Default Description
severity string No - critical/high/medium/low
type string No - bec/phishing/malware/extortion/scam/spam/supply-chain
status string No not-remediated remediated/not-remediated/post-remediated/all
start-date string No 24h ago ISO 8601 date
end-date string No now ISO 8601 date
limit int No 25 Max results (1-100)

Examples

Triage All Recent Threats

/threat-triage

Critical Threats Only

/threat-triage --severity critical

BEC Threats This Week

/threat-triage --type bec --start-date "2026-03-20T00:00:00Z"

All Threats Including Remediated

/threat-triage --status all --limit 50

Output

Abnormal Security Threat Triage (last 24 hours)
================================================

Found 8 unremediated threats

+-----------+------------------+----------+---------------------+-----------------------------------+-------------------+
| Threat ID | Attack Type      | Severity | Sender              | Subject                           | Received          |
+-----------+------------------+----------+---------------------+-----------------------------------+-------------------+
| 184def76  | BEC              | Critical | [email protected]     | Urgent: Wire Transfer Request     | 2026-03-27 09:15  |
| 29abc134  | Supply Chain     | Critical | [email protected]  | Updated Payment Details           | 2026-03-27 08:42  |
| 3f4e5d6c  | Credential Phish | High     | [email protected]| Verify Your Account               | 2026-03-27 07:30  |
| 4a5b6c7d  | Malware          | High     | [email protected] | Invoice #8821 Attached            | 2026-03-27 06:15  |
| 5b6c7d8e  | Credential Phish | High     | [email protected]   | Shared Document Ready             | 2026-03-26 22:10  |
| 6c7d8e9f  | Extortion        | Medium   | [email protected]      | We Have Your Data                 | 2026-03-26 20:45  |
| 7d8e9f0a  | Scam             | Medium   | [email protected]   | Invoice Payment Overdue           | 2026-03-26 18:30  |
| 8e9f0a1b  | Spam             | Low      | [email protected] | Limited Time Offer!               | 2026-03-26 16:00  |
+-----------+------------------+----------+---------------------+-----------------------------------+-------------------+

Summary:
- Critical: 2 | High: 3 | Medium: 2 | Low: 1
- Types: BEC (1), Supply Chain (1), Credential Phishing (2), Malware (1), Extortion (1), Scam (1), Spam (1)
- Auto-Remediated: 0 | Not Remediated: 8

Priority Actions:
1. Investigate BEC threat 184def76 - wire transfer request targeting CFO
2. Investigate Supply Chain threat 29abc134 - vendor payment redirect
3. Remediate credential phishing threats 3f4e5d6c, 5b6c7d8e

Quick Actions:
- View threat details: /search-threats --type bec
- Inspect one threat: abnormal_threats_get with the threat UUID
- Remediate: abnormal_messages_list, then abnormal_remediation_manage per message

Read the full file on GitHub · 136 lines

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. 1mo ago First seen · 136 lines · 15 tokens per session scan A 4298a8e92a81

Subscribe to this mod's changes

threat-triage is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (49 stars, last pushed 4d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,260 once invoked, about $0.0001 per session on Opus 5.5. 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.