スキル agents-md-audit

📦

agents-md-audit

Name: agents-md-audit
Author: agentkitco

v1.0 コンテンツリビジョン r2 安全 ⚙️ 外部コマンド

Audit Agent Instructions for Accuracy and Clarity

Stale commands, broken paths, and vague rules make agent instructions unreliable. This skill combines local heuristic checks with evidence-based review and proposes shorter instructions before approved edits.

対応: Claude Codex Code(CC)

📊 76 十分

Maintain this Skill? Claim it 📊 76 十分

自分のエージェントでインストール

このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。

エージェントリクエスト

Review the Skillstore skill "agents-md-audit" from https://skillstore.io/skills/agentkitco-agents-md-audit.md and its manifest at https://skillstore.io/api/skills/agentkitco-agents-md-audit/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。

エージェントが読めるリソース

AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。

Markdown詳細 GET /skills/agentkitco-agents-md-audit.md 署名済み manifest GET /api/skills/agentkitco-agents-md-audit/manifest 署名済み lockfile GET /api/skills/agentkitco-agents-md-audit/lockfile

テストする

「agents-md-audit」を使用しています。 Audit an instruction file containing a missing script reference and an obsolete directory.

期待される結果:

Must fix: The documented script has no matching definition in the repository manifest.
Must fix: The referenced directory does not exist at the documented location.
Not verified: Deployment was not run because it can change external state.
Proposed version: Remove obsolete references and retain verified instructions, pending owner approval.

「agents-md-audit」を使用しています。 Review a long instruction file with repeated rules and a possible secret.

期待される結果:

Must fix: A possible secret was detected. Its value is omitted; remove it and rotate it if real.
Should trim: A repeated rule duplicates an earlier instruction.
Should trim: Replace vague quality language with a testable requirement.
Proposed version: Keep unique hard constraints and move relevant rules into scoped files.

セキュリティ監査

安全

v2 • 2026/10/22 バージョン別レポートを開く

All 13 static findings are false positives involving regex literals, comments, Markdown formatting, dictionary access, or report placeholders. The checker reads local files and reports heuristics without executing extracted commands; the workflow separately permits safe command verification. No evidence found of prompt injection, credential extraction, or network exfiltration in the reviewed files.

スキャンされたファイル

250

解析済み行数

レビュー項目

誤検知を無視

リスク要因

⚙️ 外部コマンド (10)

scripts/audit_instructions.py:26 scripts/audit_instructions.py:27 scripts/audit_instructions.py:29 scripts/audit_instructions.py:98-147 scripts/audit_instructions.py:147-153 SKILL.md:16 SKILL.md:18 SKILL.md:19 SKILL.md:20 SKILL.md:31-49

最新の完了済み静的・セマンティック監査では、確認済みのセキュリティ検出事項は見つかりませんでした。これは、スキルに副作用がないことを証明するものではありません。

監査者: codex 監査履歴を表示 →

このレポートを共有・引用

バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。

バージョン別レポートを開く

レポートリンクをコピー

https://skillstore.io/skills/agentkitco-agents-md-audit/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdownバッジ

[![Skillstore security assessment](https://skillstore.io/badges/skills/agentkitco-agents-md-audit/security.svg)](https://skillstore.io/skills/agentkitco-agents-md-audit?utm_source=security_passport_badge)

HTMLバッジ

<a href="https://skillstore.io/skills/agentkitco-agents-md-audit?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentkitco-agents-md-audit/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/agentkitco-agents-md-audit.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

学術引用 (APA · BibTeX · CFF)

APA形式の引用

agentkitco. (2026). agents-md-audit security audit report (audit version 2) [Author version 1.0]. Skillstore. https://skillstore.io/skills/agentkitco-agents-md-audit/audits/2

BibTeX形式の引用

@techreport{agentkitco-agentkitco-agents-md-audit-2026,
  author = {agentkitco},
  title = {agents-md-audit security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/agentkitco-agents-md-audit/audits/2},
  note = {Author version 1.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agents-md-audit security audit report (audit version 2)"
version: "1.0"
type: report
authors:
  - name: "agentkitco"
date-released: "2026-10-22"
url: "https://skillstore.io/skills/agentkitco-agents-md-audit/audits/2"
identifiers:
  - type: other
    value: "skillstore:agentkitco-agents-md-audit:audit:2"
    description: "Skillstore immutable audit report identifier"

Skillstore スコア

このスコアの理由証拠の信頼度: 中

アーキテクチャ

保守性

コンテンツ

コミュニティ

仕様準拠

作成できるもの

Refresh Repository Instructions

Find stale commands and missing paths after repository changes, then propose corrections with supporting evidence.

Reconcile Agent Rules

Compare instruction files for conflicting requirements and identify rules better suited to specific paths.

Review Instructions Before Sharing

Check for possible secrets, leftover placeholders, and unclear rules without repeating sensitive values in the report.

これらのプロンプトを試す

Review One Instruction File

Audit AGENTS.md for broken paths, vague wording, placeholders, and possible secrets. Report findings without editing files or running project commands.

Check Command References

Review CLAUDE.md command references against repository definitions. Identify missing scripts and targets, and mark commands you cannot safely verify.

Compare Instruction Files

Find repository agent instruction files. Compare their rules for contradictions, duplicates, and scope problems, citing file names and line numbers.

Prepare a Shorter Revision

Audit all discovered instruction files. Propose shorter versions that preserve hard constraints and incident-based rules. Wait for approval before editing.

ベストプラクティス

Run the checker from the intended repository root and supply the instruction files explicitly.
Inspect project command definitions and use a trusted environment before running verification commands.
Require evidence for corrections, redact possible secrets, and approve proposed edits before applying them.

回避

Treating a clean heuristic report as proof that every instruction is correct.
Running deployment, migration, or deletion commands merely to verify documentation.
Removing incident-based rules or hard constraints solely to reduce file length.

よくある質問

Which instruction formats can I review?

The workflow covers AGENTS.md, CLAUDE.md, Claude rule files, Cursor rules, and GitHub Copilot instruction files.

Does the checker execute commands from instruction files?

No. It compares command references with local definitions. The separate review workflow permits safe verification commands and excludes deployment, migration, and deletion.

Does the skill edit files automatically?

The workflow requires an audit report and proposed revision, then waits for approval before editing.

What does the Python checker require?

It uses Python 3.8 or later and only standard-library modules. The instructions provide manual checking as a fallback.

Can it guarantee that no secrets remain?

No. It detects selected secret patterns. Review flagged values privately, omit them from reports, and rotate credentials when exposure is real.

How are contradictions and unclear rules handled?

The assistant reviews these manually, cites conflicting instructions, and proposes clearer wording. The script does not resolve semantic contradictions.

開発者情報

作成者

agentkitco

ライセンス

MIT

作者バージョン

v1.0

Skillstore リビジョン

バージョンに関する注意

作者が宣言したバージョンは有効な SemVer ではありません。

リポジトリ

https://github.com/agentkitco/agentkit-dev-skills/tree/a5058856442fcb89bd538b1c01f94558488bfac3/skills/agents-md-audit

参照

18efac79a818d7e997295839638fdd21906cfd1c

メンテナンスの新しさ

2026/10/22

利用状況

5 ダウンロード · 0 閲覧

ファイル構成

📁 scripts/

📄 audit_instructions.py

📄 SKILL.md

agentkitco のその他のスキル

すべて表示

📦

session-handoff

Create Clear Agent Session Handoffs

Long sessions and agent switches can lose decisions, test results, and unfinished work. This skill creates a concise HANDOFF.md with verified state and actionable next steps.

ドキュメント表示

📦

security-quick-review

Review Code Changes for Security Risks

Code changes can introduce security problems that routine reviews miss. This skill guides focused AI triage with evidence, realistic severity, and concrete fixes.

セキュリティ＆コンプライアンス表示

📦

review-my-diff

Review Your Diff Before Opening a Pull Request

Local changes can hide bugs, security gaps, and missing tests before human review. This skill guides an evidence-based review with prioritized findings and explicit verification results.

コーディング＆開発表示

📦

repro-first-debugging

Debug Bugs With Reproducible Evidence

Speculative fixes can hide causes and leave bugs unresolved. This skill guides assistants through reproduction, hypothesis testing, focused changes, and evidence-based verification.

コーディング＆開発表示

📦

prove-it-ran

Verify Tests Ran Before Reporting Completion

Passing claims can hide skipped tests, stale results, or checks that never exercised a change. This skill guides fresh verification and evidence-based completion reports.

コーディング＆開発表示

📦

safe-refactor

Refactor Code with Tests and Small Changes

Code cleanup can introduce behavior changes that are difficult to detect. This skill guides small refactoring steps with baseline tests, dependency checks, and repeated verification.

コーディング＆開発表示

すべて表示

📦