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.
npx skills add morodomi/redteam-skills --skill security-scangit clone --depth 1 https://github.com/morodomi/redteam-skillsWrote 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.
[](https://agentmods.dev/skills/morodomi/redteam-skills/security-scan)<a href="https://agentmods.dev/skills/morodomi/redteam-skills/security-scan"><img src="https://agentmods.dev/badge/skills/morodomi/redteam-skills/security-scan/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.
<a href="https://agentmods.dev/skills/morodomi/redteam-skills/security-scan"><img src="https://agentmods.dev/badge/skills/morodomi/redteam-skills/security-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.00695 |
| Opus 5.5 | $0.00013 | $0.00278 |
| Sonnet 5.5 | $0.00007 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
security-scan 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.
What it actually says
Security Scan
セキュリティスキャンを実行するスキル。エージェントを連携して脆弱性を検出し、自動でレポートを生成。
Usage
/security-scan # 現在のディレクトリをスキャン
/security-scan ./src # 指定ディレクトリをスキャン
# フルスキャン（13エージェント並列）
/security-scan ./src --full-scan
# 動的テスト有効化（--target必須）
/security-scan ./src --dynamic --target http://localhost:8000
# レポート自動生成をスキップ
/security-scan ./src --no-auto-report
# レポート後にE2Eテスト自動生成
/security-scan ./src --auto-e2e
Options
| Option | Description | Default |
|---|---|---|
| --full-scan | 全13エージェント並列実行 | Off (5 core agents) |
| --no-auto-report | 自動attack-reportをスキップ | 有効 |
| --auto-e2e | レポート後に自動E2E生成 | Off |
| --dynamic | SQLi動的テストを有効化 | Off |
| --enable-dynamic-xss | XSS動的テストを有効化 | Off |
| --target | 検証対象URL | Required if --dynamic |
| --no-sca | SCAスキャンをスキップ | Off |
| --no-memory | スキャン知見の読み書きをスキップ | Off |
Workflow
1. RECON Phase
└── recon-agent
2. SCAN Phase (parallel)
├── Core Agents (default: 5)
└── Extended Agents (--full-scan: +8)
3. REPORT Phase
└── JSON output
4. AUTO TRANSITION (unless --no-auto-report)
└── Skill(redteam-core:attack-report)
5. [OPTIONAL] E2E (if --auto-e2e)
└── Skill(redteam-core:generate-e2e)
6. LEARN Phase (unless --no-memory)
└── Save scan context to auto memory (details: reference.md)
Auto Transition
スキャン完了後、自動的にattack-reportを呼び出す:
検出件数: Critical 0, High 2, Medium 1
レポートを生成します。
Skill(redteam-core:attack-report)
--no-auto-report でスキップ可能。
Agent Integration
| Phase | Agent | Role |
|---|---|---|
| RECON | recon-agent | 情報収集・優先度付け |
| SCAN | 5 core / 13 full | 脆弱性検出（並行実行） |
Reference
詳細は reference.md を参照。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 89 lines · 33 tokens per session scan A 2857705947c1
security-scan is a skill published in the GitHub repository morodomi/redteam-skills (2 stars, last pushed 8mo ago), licensed MIT. It adds 33 tokens to every session and 695 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 2026-08-31.
Other skills, from other repositories
code-review
Rigorous review of OWASP Cheat Sheet Series pull requests across security correctness, practicality, link and source verification, duplication, and language. Use for any pull request that touches cheatsheets/ or cheatsheetsdraft/, or that adds or changes external links or citations.
security-expert
Expert-level application security, OWASP Top 10, penetration testing, and security best practices. Use when the user mentions OWASP, pentesting, appsec, vulnerability, encryption, or authentication, or when the task involves Security Principles, OWASP Top 10, Security Domains, or Broken Access Control.
owasp-security-audit
Perform OWASP-aligned security audits of source code, API handlers, mobile apps, Kubernetes manifests, LLM/agent code, and deployment configuration. Covers the OWASP Top 10 (2025), ASVS 5.0.0 (V1-V17 chapter numbering), MASVS, API Security Top 10 (2023), Kubernetes Top 10 (2022), and the OWASP LLM Top 10 (2026) plus…
secure-coding-practices
Audit code against a 14-domain secure coding checklist derived from OWASP's living sources — the Developer Guide, Cheat Sheet Series, and Proactive Controls — with the original OWASP Secure Coding Practices Quick Reference Guide noted only as the archived historical origin. Covers 14 critical domains including input…
owasp-top-10-web
Reviews web applications against the OWASP Top 10:2021 vulnerability categories. Auto-invoked when reviewing web application code, server configurations, or when a user asks for a general security review of a web application. Produces structured findings mapped to A01-A10 with CWE references, severity ratings, and…
Mixed-Language Monorepos
This skill should be used when the user is auditing a "polyglot monorepo", "multi-language codebase", "microservices with different languages", "Go + Python + TypeScript", or any codebase with services written in different programming languages. Provides strategies for cross-service security analysis and unified…