Skip to content
cccskills
FreePublished on GitHub

Multitenancy Isolation Guard

マルチテナント前提の設計差分から、テナント分離(データ/権限/リソース/障害影響)の抜けや越境リスクを検出

The English summary is being prepared. Showing the original description.

See how to install

Files included (11)

  • SKILL.md2.0 KB
  • eval/promptfoo.yaml1.8 KB
  • fixtures/01-missing-tenant-filter-happy.md1.0 KB
  • fixtures/02-proper-tenant-isolation.md1.4 KB
  • fixtures/03-shared-resource-noisy-neighbor.md1.2 KB
  • golden/01-missing-tenant-filter-happy.md868 B
  • golden/02-proper-tenant-isolation.md289 B
  • golden/03-shared-resource-noisy-neighbor.md1.6 KB
  • prompt/system.md5.4 KB
  • prompt/user.md2.8 KB
  • README.md3.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Pattern declaration

Primary pattern: Reviewer Secondary patterns: Inversion Why: マルチテナント設計の差分からテナント分離(データ/権限/リソース/障害影響)の抜けをレビューし、テナント越境シナリオを逆照射する。

Guidance

  • Confirm tenant scoping for data paths (queries, cache keys, queues, storage).
  • Check auth and authorization flows prevent cross-tenant access (IDOR, tenant headers).
  • Call out noisy-neighbor risks: shared pools, rate limits, or job queues without fairness.
  • Ensure failure isolation and observability are tenant-aware.

Non-goals

  • テナント以外の一般的な設計批評は避ける。

Pre-execution Gate / 実行前ゲート

このスキルは以下の条件がすべて満たされない限りNO_REVIEWを返す。

  • 対象ファイルにマルチテナントに関する設計・アーキテクチャドキュメントが含まれている
  • 対象ファイルにテナント分離(データアクセス・権限・リソース分離)に関する記述がある
  • inputContextにfullFileが含まれている

ゲート不成立時の出力: NO_REVIEW: multitenancy-isolation — マルチテナント設計に関する差分がない

False-positive guards

  • 既に tenant_id フィルターや RLS/名前空間化が明示されている場合、差分外の記述のみでは指摘しない。

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

<What this skill does>

The English summary is being prepared. Showing the original description.

s977043/river-review7Updated Oct 22, 2026

画像・ボタン・フォーム要素に適切なアクセシブルネームがあるか確認する。

The English summary is being prepared. Showing the original description.

s977043/river-review7Updated Oct 22, 2026

Ensure ADRs capture context, decision, alternatives, tradeoffs, and follow-ups in a way that prevents future drift.

The English summary is being prepared. Showing the original description.

s977043/river-review7Updated Oct 22, 2026

敵対的分析手法を統合したレビューの entry skill。認知バイアス対策の3手法 (Pre-mortem / War Game / Logic Torturing)と、宣言・主張と実態の乖離を突く claim-vs-actual 検出3パターン(Self-Contradiction / Refactor-Claim Audit / Cross-File Leakage)へルーティングし、通常のレビューでは見えない設計の盲点・ 防御の穴・論理の弱点・宣言と実装のズレを可視化する。

The English summary is being prepared. Showing the original description.

s977043/river-review7Updated Oct 22, 2026

Review changes to the Agent Skills import/export bridge for path safety, round-trip fidelity, and validation correctness.

The English summary is being prepared. Showing the original description.

s977043/river-review7Updated Oct 22, 2026

Checks whether AI-assisted work defines review criteria, accessible context, explicit review loop, human judgment boundary, and feedback capture before delegating to an agent.

The English summary is being prepared. Showing the original description.

s977043/river-review7Updated Oct 22, 2026

See all skills by s977043

Report a problem with this skill