Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/eaglesakura/agent-skills/mobile-security-knowledgenpx skills add eaglesakura/agent-skills --skill mobile-security-knowledgegit clone --depth 1 https://github.com/eaglesakura/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/eaglesakura/agent-skills/mobile-security-knowledge)<a href="https://agentmods.dev/skills/eaglesakura/agent-skills/mobile-security-knowledge"><img src="https://agentmods.dev/badge/skills/eaglesakura/agent-skills/mobile-security-knowledge.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00352 | $0.02594 |
| Opus 5 | $0.00176 | $0.01297 |
| Sonnet 5 | $0.00070 | $0.00519 |
| Haiku 4.5 | $0.00035 | $0.00259 |
Grade A, and why
mobile-security-knowledge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Security Knowledge
公式・OWASP 等を蒸留したセキュリティナレッジを、必要な文書だけ Context に載せて使う SKILL である。
条文の正本は同梱 references/ であり、本 Body にはセキュリティ知識そのものを書かない。
文書の書式は markdown-documentation に従っている（## 概要 / 原則+補足+実装例 / ### DO: / ### DO NOT: / ## 参考リンク）。
いつ使うか
/plan.init/ Plan モードで実装計画・関連 SKILL 適用を行うとき/coding.requirementで要件・技術要件・セキュリティ要件・暗黙要件を計画へ落とすとき/coding.designで詳細設計し、DO／推奨に沿った実装方針を書くとき/coding.loop（/loop /coding.loop）で DO NOT 監査を含む設計→実装ループを回すとき- コードレビュー・セキュリティレビューで、禁止事項（DO NOT）を洗い出すとき
- 上記以外でも、認証・権限・暗号・クラウド／Firebase／モバイル基盤の話が出たとき
Coding-Commands（plan.init / coding.requirement / coding.design / coding.loop）側は本 SKILL への直リンクを持たない。
同時利用が前提のため、それらのフローに入ったら本 SKILL を自らロードし、探査手順を適用する。
Coding-Commands / Plan 併用時の振る舞い
直リンクが無くても、次の合図があれば本 SKILL をロード済みとして扱う。
| 合図 | 本 SKILL での主作業 |
|---|---|
/plan.init / Plan モード |
主題に触れる領域の references/ を Stage 1 で当たり、関連 DO を計画提案に織り込む |
/coding.requirement |
### DO: を「セキュリティ要件」または「技術要件」（および暗黙的な要件）へ参照付きで提案する |
/coding.design |
詳細設計が DO に沿い、関連 ### DO NOT: を設計に残さない |
/coding.loop / DO NOT 監査 |
ループのゲートとして関連 DO NOT を照合し、残 0 件になるまで指摘・差し戻しする |
engineer-software-requirement / engineer-software-design が「関連 SKILL・ドキュメントの DO / DO NOT を使え」と指示している場合も、その正本探索先として本 SKILL の references/ を使う。
前提
- ナレッジの正本は同梱
references/（サイト／標準ごとのディレクトリ） - 探索手順の正本は
markdown-search（Stage 1 → 2 → 3） - 文書を新規に書く・直す作業は
markdown-documentation（本 SKILL の主用途ではない）
ディレクトリ案内（絞り込み用）
文脈が明確なら Stage 1 の対象を次に絞る。不明なら references/ 全体から始める。
| 文脈 | 優先ディレクトリ |
|---|---|
| Android 実装・マニフェスト・権限・不正対策 | references/developer.android.com/（併せて references/mas.owasp.org/） |
| iOS / Apple 開発者向けセキュリティ | references/developer.apple.com/（併せて references/mas.owasp.org/） |
| OWASP MAS / MASVS / MASTG / Best Practices / Tests（Android・iOS の知識・テスト・Best Practices を含む） | references/mas.owasp.org/ |
| Google Cloud IAM・秘密・Cloud Run 等 | references/cloud.google.com/ |
| Firebase App Check・Rules・Checklist・環境分離 | references/firebase.google.com/ |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/LICENSE.md 1.9 KB
- evals/evals.json 3.4 KB
- references/cloud.google.com/0000-index.md 3.3 KB
- references/cloud.google.com/0001-security-best-practices-catalog.md 3.5 KB
- references/cloud.google.com/0002-secure-enterprise-foundations.md 3.8 KB
- references/cloud.google.com/0003-iam.md 3.5 KB
- references/cloud.google.com/0004-secret-manager-best-practices.md 3.5 KB
- references/cloud.google.com/0005-cloud-run-ingress.md 3.7 KB
- references/developer.android.com/0000-index.md 3.2 KB
- references/developer.android.com/0001-security.md 4.2 KB
- references/developer.android.com/0002-security-tips.md 7.0 KB
- references/developer.android.com/0003-privacy-guidelines.md 4.7 KB
- references/developer.android.com/0004-fraud-prevention-environment.md 4.8 KB
- references/developer.android.com/0005-fraud-prevention-activities.md 4.0 KB
- references/developer.android.com/0006-fraud-prevention-authentication.md 5.2 KB
- references/developer.apple.com/0001-security.md 4.7 KB
- references/firebase.google.com/0000-index.md 3.2 KB
- references/firebase.google.com/0001-security-checklist.md 4.2 KB
- references/firebase.google.com/0002-app-check.md 4.0 KB
- references/firebase.google.com/0003-security-rules.md 3.3 KB
- references/firebase.google.com/0004-iam.md 3.1 KB
- references/firebase.google.com/0005-dev-workflow-security-guidelines.md 3.7 KB
- references/mas.owasp.org/0001-mas-overview.md 3.5 KB
- references/mas.owasp.org/0002-masvs.md 11 KB
- references/mas.owasp.org/0003-maswe.md 6.3 KB
- references/mas.owasp.org/0004-mastg.md 3.9 KB
- references/mas.owasp.org/0005-mas-checklists.md 3.4 KB
- references/mas.owasp.org/android-testing/0000-index.md 3.9 KB
- references/mas.owasp.org/android-testing/0001-0x05a-platform-overview.md 4.5 KB
- references/mas.owasp.org/android-testing/0002-0x05b-android-security-testing.md 3.5 KB
- references/mas.owasp.org/android-testing/0003-0x05d-testing-data-storage.md 3.7 KB
- references/mas.owasp.org/android-testing/0004-0x05e-testing-cryptography.md 3.4 KB
- references/mas.owasp.org/android-testing/0005-0x05f-testing-local-authentication.md 3.5 KB
- references/mas.owasp.org/android-testing/0006-0x05g-testing-network-communication.md 2.6 KB
- references/mas.owasp.org/android-testing/0007-0x05h-testing-platform-interaction.md 2.8 KB
- references/mas.owasp.org/android-testing/0008-0x05i-testing-code-quality-and-build-settings.md 3.1 KB
- references/mas.owasp.org/android-testing/0009-0x05j-testing-resiliency-against-reverse-engineering.md 3.6 KB
- references/mas.owasp.org/best-practices/0000-index.md 16 KB
- references/mas.owasp.org/best-practices/android/0001-MASTG-BEST-0001.md 4.2 KB
- references/mas.owasp.org/best-practices/android/0002-MASTG-BEST-0002.md 3.8 KB
- references/mas.owasp.org/best-practices/android/0003-MASTG-BEST-0003.md 5.0 KB
- references/mas.owasp.org/best-practices/android/0004-MASTG-BEST-0004.md 3.8 KB
- references/mas.owasp.org/best-practices/android/0005-MASTG-BEST-0005.md 3.5 KB
- references/mas.owasp.org/best-practices/android/0006-MASTG-BEST-0006.md 3.8 KB
- references/mas.owasp.org/best-practices/android/0007-MASTG-BEST-0007.md 4.1 KB
- references/mas.owasp.org/best-practices/android/0008-MASTG-BEST-0008.md 4.0 KB
- references/mas.owasp.org/best-practices/android/0009-MASTG-BEST-0009.md 3.3 KB
- references/mas.owasp.org/best-practices/android/0010-MASTG-BEST-0010.md 5.0 KB
- references/mas.owasp.org/best-practices/android/0011-MASTG-BEST-0011.md 4.7 KB
- references/mas.owasp.org/best-practices/android/0012-MASTG-BEST-0012.md 5.7 KB
- references/mas.owasp.org/best-practices/android/0013-MASTG-BEST-0013.md 4.3 KB
- references/mas.owasp.org/best-practices/android/0014-MASTG-BEST-0014.md 4.1 KB
- references/mas.owasp.org/best-practices/android/0015-MASTG-BEST-0015.md 3.4 KB
- references/mas.owasp.org/best-practices/android/0016-MASTG-BEST-0016.md 3.3 KB
- references/mas.owasp.org/best-practices/android/0017-MASTG-BEST-0017.md 3.2 KB
- references/mas.owasp.org/best-practices/android/0018-MASTG-BEST-0018.md 3.4 KB
- references/mas.owasp.org/best-practices/android/0019-MASTG-BEST-0019.md 3.3 KB
- references/mas.owasp.org/best-practices/android/0020-MASTG-BEST-0020.md 4.1 KB
- references/mas.owasp.org/best-practices/android/0021-MASTG-BEST-0021.md 5.9 KB
- references/mas.owasp.org/best-practices/android/0027-MASTG-BEST-0027.md 3.3 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 144 lines · 352 tokens per session scan A 05fbdfeb2c39
mobile-security-knowledge is a skill published in the GitHub repository eaglesakura/agent-skills (2 stars, last pushed today), licensed MIT. It adds 352 tokens to every session and 2,594 once invoked, about $0.0018 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.