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 thkt/dotclaude --skill use-context-reviewer-securitygit clone --depth 1 https://github.com/thkt/dotclaudeWrote 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/thkt/dotclaude/use-context-reviewer-security)<a href="https://agentmods.dev/skills/thkt/dotclaude/use-context-reviewer-security"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/use-context-reviewer-security.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.01871 |
| Opus 5 | $0.00024 | $0.00936 |
| Sonnet 5 | $0.00010 | $0.00374 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
use-context-reviewer-security scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| A10 | SSRF | `fetch(userInputUrl)` | URL バリデーション、許可リスト | How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
use-context-reviewer-security
検出 (OWASP Top 10)
LLM01 は信頼できないコンテンツを LLM に渡すアプリを対象とする。sink はプロンプトそのものであり、データと指示の境界なく連結された信頼できないテキストや、システムプロンプトに補間された呼び出し側の値が該当する。fetch_url のような LLM ツールは、A10 SSRF など非 LLM の対応物と同じように制約する。sink はツールであってプロンプトではない。
| ID | カテゴリ | パターン | 修正 |
|---|---|---|---|
| LLM01 | Prompt Injection (LLM) | RAG ドキュメント・取得コンテンツ・ツール結果・role 引数など、信頼できない値や呼び出し側が制御する値が、データとしての枠付けなしにプロンプトへ到達 | 信頼できないコンテンツをデータとして区切る。呼び出し側の値は固定の列挙された指示にマッピングする |
| A01 | Broken Access Control | 認証なし、IDOR、path traversal | 認証ミドルウェア、所有権チェック |
| A01 | CSRF | 状態変更リクエスト (POST/PUT/PATCH/DELETE) に CSRF トークン検証なし | Double Submit Cookie |
| A01 | Open Redirect (Taint) | URL パラメータ → location.href でバリデーションなし |
ドメイン許可リストまたは相対のみ |
| A02 | Cryptographic Failures | password: 'plaintext' |
bcrypt/argon2 ハッシュ化 |
| A02 | Timing Attack | トークン/署名の === 比較 |
定数時間比較。全バイトを XOR し最後に判定 |
| A02 | Sensitive Data Exposure | localStorage/sessionStorage に保存された JWT | httpOnly cookie に置き換える |
| A03 | Injection | db.query(\SELECT...${id}`)` |
パラメータ化クエリ、ORM |
| A03 | Injection | exec(\ping ${host}`)` |
入力バリデーション、ライブラリで代替 |
| A03 | XSS | 静的に存在する dangerouslySetInnerHTML |
デフォルト エスケープ、DOMPurify |
| A03 | XSS (Taint) | サニタイザなしの dangerouslySetInnerHTML={{ __html }} |
境界で DOMPurify.sanitize() を呼ぶ |
| A03 | XSS (Taint) | 関数引数 → innerHTML でサニタイズなし |
関数境界でサニタイズ |
| A03 | XSS (Taint) | ユーザー制御 URL を持つ <a href={variable}> |
https/http のみのプロトコル許可リスト |
| A04 | Insecure Design | origin チェックなしの postMessage ハンドラ |
event.origin の厳密比較 |
| A05 | Security Misconfiguration | cors({ origin: '*' }) |
明示的な origin 許可リスト |
| A05 | Security Misconfiguration | オプションなしの cookie: {} |
secure, httpOnly, sameSite: 'strict' |
| A05 | Security Misconfiguration | エラー応答の err.stack で NODE_ENV ガードなし |
本番では汎用メッセージ、内部だけにログ |
| A07 | Authentication Failures | 認証エンドポイント (login, register, password-reset) にレート制限なし | auth ルートグループに rate limiter ミドルウェア |
| A08 | Prototype Pollution | ...body スプレッドでリクエストオブジェクト構築 |
明示的なフィールド代入 |
| A09 | Logging Failures | logger.info({ password }) |
センシティブ フィールドを除外 |
| A10 | SSRF | fetch(userInputUrl) |
URL バリデーション、許可リスト |
What ships with it
8 files 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.
- 7d ago First seen · 72 lines · 49 tokens per session scan A fb513fcb138a
use-context-reviewer-security is a skill published in the GitHub repository thkt/dotclaude (12 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 1,871 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
team-management-receiving-feedback
How to receive code review as technical evaluation rather than social performance — verify claims against the codebase before implementing, push back with evidence, and drop the performative agreement. Use when responding to a human reviewer, a PR comment, or another AI reviewer, and when deciding whether a suggestion…
mindforge-review
Request cross-AI peer review of phase plans from external AI CLIs.
mindforge-pr-branch
Create a clean PR branch by filtering out .planning/ commits — ready for code review.
mindforge-ship
Create PR, run review, and prepare for merge after verification passes.
review
Adversarial design review of a System Design Doc. Interrogates the staff questions, finds the cost-explosion and failure risks, returns a verdict. Sensors and evals gate.
pr-reviewer
Review pull requests with full context. Fetches linked Jira tickets, Figma designs, and Notion docs via MCP, spawns parallel subagents for systematic code review (correctness, security, tests, SOLID, clean code), then drafts friendly, humanized GitHub-ready comments. Use when reviewing PRs, examining code changes, or…