Skip to content
cccskills
FreePublished on GitHub

Baseline Security Checks

Check common security risks in application code (SQLi, XSS, secrets, open redirect).

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

See how to install

Files included (17)

  • SKILL.md3.5 KB
  • eval/promptfoo.yaml4.8 KB
  • fixtures/01-sql-injection-happy.md955 B
  • fixtures/02-false-positive-test.md935 B
  • fixtures/03-open-redirect-backslash-happy.md1.5 KB
  • fixtures/04-open-redirect-relative-path-allowlist-guard.md1.7 KB
  • fixtures/05-open-redirect-null-host-bypass-happy.md1.8 KB
  • fixtures/06-lexical-path-exemption-happy.md1.5 KB
  • golden/01-sql-injection-happy.md592 B
  • golden/02-false-positive-test.md455 B
  • golden/03-open-redirect-backslash-happy.md1.1 KB
  • golden/04-open-redirect-relative-path-allowlist-guard.md569 B
  • golden/05-open-redirect-null-host-bypass-happy.md1.1 KB
  • golden/06-lexical-path-exemption-happy.md864 B
  • prompt/system.md5.2 KB
  • prompt/user.md2.1 KB
  • README.md3.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Pattern declaration

Primary pattern: Reviewer Secondary patterns: Inversion Why: セキュリティチェックはチェックリスト型評価が主だが、セキュリティ無関係の変更では実行を止めるゲートが必要

Guidance

  • Look for string-concatenated queries or unsafe ORM calls; require parameterization.
  • Flag unescaped HTML sinks (dangerouslySetInnerHTML/innerHTML) and missing sanitization.
  • Catch secrets or tokens hardcoded in code; prefer environment/config inputs.
  • Ensure input validation and authz/CSRF/error handling paths exist without leaking sensitive detail.
  • Open redirect: a return URL may pass a same-host check by a server-side parser (e.g. PHP parse_url), then reach Location / redirect() / href. Check that values containing \ are rejected before that check.
    • PHP parse_url('http://evil.example\\@self.example/', PHP_URL_HOST) returns self.example.
    • Browsers (WHATWG URL) treat \ as / and navigate to evil.example.
    • If the value is decoded again after the check (double encoding, a later urldecode), reject %5C as well.
    • Rejecting \ / %5C alone is not enough. A check that skips values without a parse_url host lets http:evil.example and /<TAB>/evil.example through. Browsers resolve both to evil.example.
    • Raise confidence when a sibling implementation in the same repository already rejects \ / %5C.
  • Lexical-shape exemptions: when a diff adds or widens an allowlist that skips masking/validation because a value looks like a path or variable reference, check non-canonical forms that would wrongly hit it (.. segments, empty segments //, trailing delimiters, case variants, %2F, a second assignment on the same line), and expect tests pinning that those forms stay masked/rejected.

Non-goals

  • テスト用ダミー値や意図された緩和を推測で脆弱と決めつけない。

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。

  • 差分にアプリケーションコード(api/, routes/, db/, auth/等)の変更が含まれている
  • 差分がテストファイルやフィクスチャのみでない
  • 外部入力の処理、認証/認可、データ永続化のいずれかに関連するコードが含まれている

ゲート不成立時の出力: NO_REVIEW: security-basic — セキュリティ関連のアプリケーションコード変更が検出されない

False-positive guards

  • 環境変数経由や既存バリデーションが確認できる場合は黙る。
  • 戻り先 URL が次の両方を満たすときだけ、open redirect として指摘しない。
    • \ と制御文字を含む値を拒否している。
    • 先頭が単一の /(// と /\ は除く)の相対パスだけを許可しているか、WHATWG 相当のパーサーで解決した URL の origin を自サイトと比較している。
  • \ / %5C を拒否しているだけで、parse_url のホストが無い値を素通しする判定は抑制条件に当たらない。

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 23, 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 23, 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 23, 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 23, 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 23, 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 23, 2026

See all skills by s977043

Report a problem with this skill