<Skill Name>
Free<What this skill does>
The English summary is being prepared. Showing the original description.
Reviews GitHub Actions workflow diffs for script injection of untrusted input, pull_request_target with untrusted checkout, over-broad GITHUB_TOKEN permissions, and unpinned third-party actions.
The English summary is being prepared. Showing the original description.
Review the instructions the agent will receive before you install.
Primary pattern: Reviewer Secondary patterns: Inversion Why: workflow の意味的なセキュリティ判断(権限の必要性・トリガーの用途)に集中し、決定論ツールが見ない文脈を検査する
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。
.github/workflows/ 配下の追加変更が含まれているゲート不成立時の出力: NO_REVIEW: gha-workflow-security — workflow の変更なし
./.github/actions/...、自 org reusable workflow)はピン留め不要とする運用が一般的。minor 以下に留める。actions/* 公式 action の tag 運用は third-party より低リスク。minor 扱い。if: 条件式内の式展開、github.event.*.number / github.sha / github.actor 等の数値・制約付きフィールドは原則安全。pull_request_target は安全パターン。github.event.issue.title/.body、pull_request.title/.body/.head.ref、comment.body、commits.*.message、github.head_ref 等)を run: に直接式展開しない。env: 経由で変数化する。pull_request_target / issue_comment / workflow_run で head.sha / head.ref を checkout して PR 由来コードを実行しない(secrets + write 権限の文脈での RCE)。permissions は top-level を contents: read にし、write は必要な job 単位で昇格する(write-all を避ける)。<file>:<line> で差分に紐づけ、出典(securitylab.github.com / docs.github.com の secure-use)を 1 行で添える。run: 直挿し / pull_request_target + head checkout = critical、permissions 過剰 / public self-hosted = major、tag ピン / persist-credentials = minor。コメントは日本語で返す。
No reviews yet. Tell others what you thought.
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.
<What this skill does>
The English summary is being prepared. Showing the original description.
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.
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.
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.
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.
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.