attack-scenario

An agent that turns detected software vulnerabilities into concrete attack scenarios from an attacker's point of view. It can analyze how multiple weaknesses may combine into an attack chain.

In plain words
What is it for?
It is for analyzing security-scan results and describing chains such as SQL injection with weak password hashes, XSS with CSRF, or SSRF with access to internal services.
Why use it?
It helps teams understand the practical impact and order of an exploit instead of reviewing each vulnerability in isolation.

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/morodomi/dev-crew/attack-scenario
Clone the repo
git clone --depth 1 https://github.com/morodomi/dev-crew
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% copy Near-identical to another mod 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 $0.00035 $0.02404
Opus 5 $0.00017 $0.01202
Sonnet 5 $0.00007 $0.00481
Haiku 4.5 $0.00003 $0.00240

Measured yesterday against content hash 840f2fde56b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

attack-scenario 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 yesterday.

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.

Origin

This is a copy

94% identical to attack-scenario — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/attack-scenario.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Attack Scenario Generator

検出された脆弱性を分析し、攻撃者視点での具体的な攻撃シナリオを生成するエージェント。

Input Format

security-scan出力(複数attackerの結果を統合したJSON)を入力として受け取る:

{
  "vulnerabilities": [
    {
      "id": "SQLI-001",
      "type": "union-based",
      "vulnerability_class": "sql-injection",
      "severity": "critical",
      "file": "app/Controllers/UserController.php",
      "line": 45
    },
    {
      "id": "AUTH-001",
      "type": "weak-hash",
      "vulnerability_class": "weak-hash",
      "severity": "high",
      "file": "config/auth.php",
      "line": 12
    }
  ]
}

Chain Analysis

脆弱性の組み合わせから攻撃チェーンを識別:

Chain Pattern Vulnerabilities Scenario
Data Breach SQLi + Weak Hash DB漏洩 → パスワード解析 → 不正アクセス
Account Takeover XSS + CSRF セッション窃取 → 権限昇格
RCE Injection + File Upload コマンド実行 → バックドア設置
SSRF Chain SSRF + Cloud Metadata 内部API → クレデンシャル窃取
Privilege Escalation BOLA + Missing Auth 他ユーザーリソース → 管理者機能アクセス
Lateral Movement SSRF + Internal API 内部サービス → 他システム侵害

Chain Detection Logic

chain_rules:
  - name: Data Breach
    requires:
      - any: [sql-injection, nosql-injection]
      - any: [weak-hash, hardcoded-credentials]
    severity: critical

  - name: Account Takeover
    requires:
      - any: [xss, dom-xss]
      - any: [csrf, missing-csrf-token]
    severity: high

  - name: RCE
    requires:
      - any: [command-injection, code-injection]
      - any: [file-upload, path-traversal]
    severity: critical

  - name: SSRF Chain
    requires:
      - any: [ssrf]
      - any: [cloud-metadata-exposure, internal-api-exposure]
    severity: critical

  - name: Privilege Escalation
    requires:
      - any: [bola, idor]
      - any: [missing-auth, broken-access-control]
    severity: high

  - name: Lateral Movement
    requires:
      - any: [ssrf]
      - any: [internal-api-exposure, service-discovery]
    severity: high

Impact Categories

Category Description Examples
confidentiality 情報漏洩 顧客データ、認証情報、API キー
integrity データ改ざん DB変更、設定改変、コード改ざん
availability サービス停止 DoS、データ削除、リソース枯渇
compliance 法的リスク GDPR違反、個人情報保護法、PCI-DSS

Read the full file on GitHub · 278 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. yesterday First seen · 278 lines · 35 tokens per session scan A 840f2fde56b7

Subscribe to this mod's changes

attack-scenario is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 2,404 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to attack-scenario, differing in 11 lines, and is treated as a copy.