本文へ移動
cccskills
無料GitHub で公開

kelly-appsec

审计已获授权的应用与 REST API 的对象、字段、动作权限及业务规则,维护接口清单、身份矩阵、可归属证据和指定版本复测。

Use for application/API authorization audits, tenant isolation, business logic security and source review; not Linux incident response.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skillsスター 5(GitHub 5 + cccskills 0)

実行スコア 未検証

インストール方法を見る

含まれるファイル(113)

  • SKILL.md4.7 KB
  • agents/openai.yaml294 B
  • assets/recordings/kelly-appsec-zh-CN.mp4132 B
  • assets/recordings/kelly-appsec.mp4132 B
  • assets/screenshots/cover-zh-CN.webp130 B
  • assets/screenshots/cover.webp130 B
  • assets/screenshots/endpoints-zh-CN.webp130 B
  • assets/screenshots/endpoints.webp130 B
  • assets/screenshots/findings-mobile-zh-CN.webp130 B
  • assets/screenshots/findings-mobile.webp130 B
  • assets/screenshots/findings-zh-CN.webp130 B
  • assets/screenshots/findings.webp130 B
  • assets/screenshots/matrix-zh-CN.webp130 B
  • assets/screenshots/matrix.webp130 B
  • assets/screenshots/overview-zh-CN.webp130 B
  • assets/screenshots/overview.webp130 B
  • assets/screenshots/projects-zh-CN.webp130 B
  • assets/screenshots/projects.webp130 B
  • assets/screenshots/rules-zh-CN.webp130 B
  • assets/screenshots/rules.webp130 B
  • assets/screenshots/runs-zh-CN.webp130 B
  • assets/screenshots/runs.webp130 B
  • assets/screenshots/thumbs/cover-zh-CN.webp130 B
  • assets/screenshots/thumbs/cover.webp130 B
  • assets/screenshots/thumbs/endpoints-zh-CN.webp130 B
  • assets/screenshots/thumbs/endpoints.webp130 B
  • assets/screenshots/thumbs/findings-mobile-zh-CN.webp130 B
  • assets/screenshots/thumbs/findings-mobile.webp130 B
  • assets/screenshots/thumbs/findings-zh-CN.webp130 B
  • assets/screenshots/thumbs/findings.webp130 B
  • assets/screenshots/thumbs/matrix-zh-CN.webp130 B
  • assets/screenshots/thumbs/matrix.webp130 B
  • assets/screenshots/thumbs/overview-zh-CN.webp130 B
  • assets/screenshots/thumbs/overview.webp130 B
  • assets/screenshots/thumbs/projects-zh-CN.webp129 B
  • assets/screenshots/thumbs/projects.webp129 B
  • assets/screenshots/thumbs/rules-zh-CN.webp130 B
  • assets/screenshots/thumbs/rules.webp130 B
  • assets/screenshots/thumbs/runs-zh-CN.webp129 B
  • assets/screenshots/thumbs/runs.webp129 B
  • blueprint.json38.1 KB
  • busabase.json2.0 KB
  • content/_folder.json679 B
  • content/checks/base.json4.9 KB
  • content/endpoints/base.json2.9 KB
  • content/evidence/base.json3.7 KB
  • content/findings/base.json5.8 KB
  • content/kelly-appsec-app/_node.json732 B
  • content/kelly-appsec-app/.busabaseignore97 B
  • content/kelly-appsec-app/.gitignore32 B
  • content/kelly-appsec-app/app/base-ui.css21.7 KB
  • content/kelly-appsec-app/app/index.html3.3 KB
  • content/kelly-appsec-app/app/js/app.js25.7 KB
  • content/kelly-appsec-app/app/js/busabase-client.js952 B
  • content/kelly-appsec-app/app/js/config.js29.9 KB
  • content/kelly-appsec-app/app/js/coverage.js6.9 KB
  • content/kelly-appsec-app/app/js/dialogs.js9.1 KB
  • content/kelly-appsec-app/app/js/messages.js4.1 KB
  • content/kelly-appsec-app/app/js/model.js5.7 KB
  • content/kelly-appsec-app/app/js/providers/busabase-provider.js4.9 KB
  • content/kelly-appsec-app/app/js/providers/demo-provider.js10.0 KB
  • content/kelly-appsec-app/app/js/providers/index.js256 B
  • content/kelly-appsec-app/app/js/runtime.js2.7 KB
  • content/kelly-appsec-app/app/js/validation.js12.0 KB
  • content/kelly-appsec-app/app/js/views.js13.7 KB
  • content/kelly-appsec-app/app/styles.css27.1 KB
  • content/kelly-appsec-app/app/styles/editorial.css30.8 KB
  • content/kelly-appsec-app/app/styles/style-picker.css4.0 KB
  • content/kelly-appsec-app/app/styles/style-picker.js13.1 KB
  • content/kelly-appsec-app/app/vendor/busabase-airapp-gate.css6.1 KB
  • content/kelly-appsec-app/app/vendor/busabase-airapp-gate.js11.2 KB
  • content/kelly-appsec-app/app/vendor/busabase-airapp.js775.9 KB
  • content/kelly-appsec-app/app/vendor/busabase-sdk.js1.1 MB
  • content/kelly-appsec-app/package.json978 B
  • content/kelly-appsec-app/pnpm-lock.yaml5.2 KB
  • content/kelly-appsec-app/pnpm-workspace.yaml63 B
  • content/kelly-appsec-app/scripts/check-editorial.mjs6.1 KB
  • content/kelly-appsec-app/scripts/check.mjs2.9 KB
  • content/kelly-appsec-app/server.js3.6 KB
  • content/kelly-appsec-files/_node.json605 B
  • content/operating-guide.md2.4 KB
  • content/projects/base.json2.6 KB
  • content/projects/records.ndjson1.2 KB
  • content/rules/base.json4.2 KB
  • content/runs/base.json4.8 KB
  • lib/domain.mjs254 B
  • lib/inventory.mjs2.5 KB
  • lib/offline.mjs5.8 KB
  • lib/prompts.mjs1.7 KB
  • lib/publish.mjs1.2 KB
  • lib/report.mjs6.9 KB
  • lib/runner.mjs23.7 KB
  • lib/store.mjs4.4 KB
  • LICENSES/Apache-2.0.txt11.0 KB
  • package.json445 B
  • pnpm-lock.yaml4.3 KB
  • pnpm-workspace.yaml63 B
  • README.md5.0 KB
  • references/audit.md3.3 KB
  • references/inventory.example.json1.2 KB
  • references/resource-map.md2.7 KB
  • references/skill-prompts.json925 B
  • references/upstream-sources.json2.9 KB
  • references/upstream.md1.1 KB
  • scripts/check.mjs1.6 KB
  • scripts/import.mjs1.7 KB
  • scripts/report.mjs1.4 KB
  • scripts/review.mjs1.1 KB
  • scripts/run.mjs2.7 KB
  • scripts/setup.mjs3.4 KB
  • scripts/sync-content.mjs7.2 KB
  • test/domain.test.mjs3.0 KB
  • test/runner.test.mjs14.5 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Kelly AppSec

以具体业务规则为起点,核对身份、对象、动作和敏感字段,保留证据后交给人复核。页面管理审计工作;实际目标请求始终由本机 Agent 在本次授权下执行。

安装与连接

npx busabase-cli@latest install ./skills/kelly-appsec
cd skills/kelly-appsec
pnpm install --frozen-lockfile
BUSABASE_BASE_URL=http://localhost:4111 node scripts/setup.mjs --apply

Cloud 使用用户明确指定的 BUSABASE_BASE_URL、BUSABASE_SPACE_ID 和本机环境中的 BUSABASE_API_KEY;不把连接凭据写入项目、任务、网页或报告。安装创建独立 Folder、七个 Base、原生表格 Views、指南 Doc、报告 Drive、本手册和 AirApp。可用 ?demo=1 查看纯本地合成演示;演示不会连接目标。

操作顺序

  1. 在“项目”登记负责人、仓库/部署版本、环境、明确 Origin 和业务授权边界。示例项目必须复制为实际项目并完成配置。
  2. 导入 OpenAPI 3/Swagger 2 JSON 或版本绑定的接口/规则 JSON。接口清单并不等于安全验证。使用 references/inventory.example.json 格式,并由业务负责人确认 allow/deny、身份、受控对象、字段断言和正向基线。
  3. 源码审计遵循 references/audit.md。本机 Agent 阅读授权仓库中的认证中间件、服务端权限及业务流程,记录具体文件行、版本、推理和限制;通过 scripts/review.mjs 导入审阅结果。不要把关键词匹配、依赖列表或空扫描当成已完成通用 SAST。
  4. 动态验证先在网页选择有限规则并创建任务,然后按下述命令在本机领取。每次独立确认项目、Origin、环境、版本、授权引用、HTTP 方法、精确路径和测试对象;任务中保存的数据不能扩大本机授权。只使用合成账号和合成测试数据。
  5. 从权限矩阵查看每个身份的预期、结果与证据。“未覆盖”“不确定”和中断项必须保留。发现只标为“待复核”;人提交理由后才确认漏洞或解释业务例外。
  6. 修复后先更新项目版本并导入该版本的相同业务规则,创建与原发现绑定的复测。规则语义、端点/方法/身份、字段断言和正向基线必须匹配;只有对应规则在新版本成功验证后才标为修复已验证。
  7. 导出带来源、版本、范围和未覆盖项的报告。页面导出只含已加载页;scripts/report.mjs 显式分页导出并标明截断。

有限动态执行

BUSABASE_BASE_URL=http://localhost:4111 \
APPSEC_TOKEN_USER_A='local-synthetic-token' \
node scripts/run.mjs --run RUN_ID --project PROJECT_ID \
  --origin https://staging.example.test --environment staging --revision COMMIT \
  --scope AUTHORIZATION_REFERENCE --allow-method GET \
  --allow-path /orders/test-a --allow-path /orders/test-b \
  --allow-object test-a --allow-object test-b --request-limit 10 \
  --directory /private/local-evidence --apply

没有 --apply 只预检。身份 user-a 读取本机 APPSEC_TOKEN_USER_A;anonymous 强制不带 token。最多 5 个端点、50 条规则、100 次请求;并发 1,每秒最多 1 次,单次 10 秒,响应 1 MiB;不跟随重定向,不展开域名、路径模板或发现的新目标。写操作额外要求 --allow-mutations,且逐条规则声明 mutating。中断不自动重试;明确 --resume 后保留 attempt 历史和请求预算。活跃 claim 不能被另一 Agent 领取;网页取消只停止后续请求。

原始响应保存在本机 0700 目录内的 0600 独占文件,拒绝符号链接目录。仅脱敏摘要、哈希、合成身份、来源和覆盖限制同步工作区。实际秘密、用户数据、Authorization/cookie 不得写入证据字段;本机原件需要按客户证据政策保管。

参见 审计方法、资源与状态、来源与许可证。不执行全网扫描、任意脚本或通用漏洞利用;HTTP 200、拒绝状态码或缺少异常均不能单独证明权限正确或已被入侵。

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

Align all AI coding agents to a single source of truth. AGENTS.md for rules, .agents/skills/ for skills, symlinks for everything else. Use when setting up a repo for multiple agents, or when links are missing, broken, or out of date.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月28日 更新

Read, answer and post on the Buda community forum at community.buda.im through its /api/v1/community REST API. Lists categories and posts, reads a thread with its replies, searches, and publishes posts and replies behind an explicit confirmation. Use when the user invokes $buda-community or /buda-community, asks what is happening in the Buda community, wants an unanswered question triaged or answered, or wants something posted or announced there.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月28日 更新

Read, answer and post on the Busabase community forum at community.busabase.com through its /api/v1/community REST API. Lists categories and posts, reads a thread with its replies, searches, and publishes posts and replies behind an explicit confirmation. Use when the user invokes $busabase-community or /busabase-community, asks what is happening in the Busabase community, wants an unanswered question triaged or answered, or wants something posted or announced there.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月28日 更新

kelly-ads

無料

Ad-campaign command desk (投放指挥台, Busabase App-in-Skill) for a cross-border e-commerce seller running Amazon Ads, Meta (FB/IG), TikTok Ads, and Google Ads. Use when the user invokes $kelly-ads or /kelly-ads, or asks about 投放, ad campaigns, ad spend, ACOS, ROAS, Amazon Ads, TikTok ads, Meta ads, Google Ads, search terms, negative keywords, bid adjustment, budget pacing, CPC spikes, rejected ads, ad anomaly detection, 广告优化, or reviewing agent-proposed adjustment cards (negative keyword, bid down/up, pause target, budget shift, creative refresh).

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月28日 更新

Busabase-backed App-in-Skill low-code agent configuration and governance console for a platform team. Use when the user invokes $kelly-agent-builder or /kelly-agent-builder, wants to review or edit a catalog of mock LLM agent configs, check quota usage, find configs that need attention, move a draft to live, pause a live agent, or archive an agent. Mock config/governance console only — it never provisions or calls any real agent.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月28日 更新

Review board (Busabase App-in-Skill) that runs a fixed suite of mock test cases against a baseline vs candidate agent version and surfaces rubric-scored regressions before a release. Use when the user invokes $kelly-agent-eval or /kelly-agent-eval, wants to review agent-version regressions, compare baseline vs candidate quality, triage a release, or record a release approve/block decision. Deterministic mock rubric scores only — not a real LLM-judge call, and it never deploys anything.

日本語の概要は準備中です。原文の説明を表示しています。

mr-kelly/skills52026年10月28日 更新

mr-kelly のスキルをすべて見る

このスキルの問題を報告する