search-threats

search-threats is a command for Claude Code from WYRE-AI/msp-claude-plugins. It costs 19 tokens per session (1,158 once invoked), scanned A, original, Apache-2.0.

A command for finding email threats detected by Abnormal Security, an email-security service, using filters such as sender, recipient, attack type, keywords, status, and dates.

In plain words
What is it for?
Use it to investigate phishing, malware, scams, spam, and other listed threat types through the Abnormal Security API.
Why use it?
It avoids manually sorting through all detected threats to find relevant messages.

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 Use it to investigate phishing, malware, scams, spam, and other listed threat types through the Abnormal Security API.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/wyre-ai/msp-claude-plugins/search-threats
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 search-threats

README.md
[![agentmods](https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/search-threats/github.svg)](https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/search-threats)
Your own site
<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/search-threats"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/search-threats/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 search-threats

Your own site · 80×15
<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/search-threats"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/search-threats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,158 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 $0.00019 $0.01158
Opus 5.5 $0.00008 $0.00463
Sonnet 5.5 $0.00004 $0.00232
Haiku 4.5 $0.00002 $0.00116

Measured 1mo ago against content hash 113fb2238ee8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

search-threats 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/search-threats.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search Threats

Search and filter email threats detected by Abnormal Security using various criteria.

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
    • Construct OData filter expression
    • Validate date range
  2. Execute search query

    GET /v1/threats?filter=...&pageSize=...
    Authorization: Bearer <token>
    
  3. Format and return results

    • Display threat list with key details
    • Include AI-generated insights for each threat

Parameters

Parameter Type Required Default Description
query string No - Free text search
type string No - bec/phishing/malware/extortion/scam/spam/supply-chain
sender string No - Sender email address or domain
recipient string No - Target recipient address
status string No all remediated/not-remediated/post-remediated/all
start-date string No 7d ago ISO 8601 date
end-date string No now ISO 8601 date
limit int No 25 Max results (1-100)

Examples

Search by Attack Type

/search-threats --type bec

Threats from a Specific Sender

/search-threats --sender "[email protected]"

Threats Targeting Finance Team

/search-threats --recipient "[email protected]"

BEC Threats This Month

/search-threats --type bec --start-date "2026-03-01" --limit 50

Search by Keyword

/search-threats --query "wire transfer"

Supply Chain Threats

/search-threats --type supply-chain --start-date "2026-03-01"

Output

Found 3 threats matching criteria (last 7 days)

+-----------+-----------+----------+---------------------+-----------------------------------+-------------------+-----------+
| Threat ID | Type      | Severity | Sender              | Subject                           | Received          | Status    |
+-----------+-----------+----------+---------------------+-----------------------------------+-------------------+-----------+
| 184def76  | BEC       | Critical | [email protected]     | Urgent: Wire Transfer Request     | 2026-03-27 09:15  | Not Remed |
| 29abc134  | BEC       | High     | [email protected]     | Confidential: Payment Update      | 2026-03-25 14:20  | Remediated|
| 3f4e5d6c  | BEC       | High     | [email protected]      | Employee Direct Deposit Change    | 2026-03-23 11:05  | Remediated|
+-----------+-----------+----------+---------------------+-----------------------------------+-------------------+-----------+

Summary:
- Critical: 1 | High: 2
- Unremediated: 1 | Remediated: 2

AI Insights (threat 184def76):
- Display name matches internal CEO but email domain is typosquat
- Reply-to address differs from sender address
- Financial request with urgency language detected
- First-time sender from this domain

Quick Actions:
- View threat details: Use abnormal_threats_get with the threat UUID
- Triage all threats: /threat-triage
- Enumerate the threat's messages: Use abnormal_messages_list

Read the full file on GitHub · 162 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 · 162 lines · 19 tokens per session scan A 113fb2238ee8

Subscribe to this mod's changes

search-threats 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 19 tokens to every session and 1,158 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.