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 skills add MingyiSecLab/Mingyi-Atlas --skill mobilegit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/mobile)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/mobile"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/mobile/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/mobile"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/mobile.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.00702 |
| Opus 5 | $0.00019 | $0.00351 |
| Sonnet 5 | $0.00008 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
mobile 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 9d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Application Red Team — Category Overview
This is a routing skill. Identify the target platform and the relevant attack surface, then load the specialized sub-skill.
Sub-Skills
| Sub-Skill | Covers | When to Load |
|---|---|---|
| android | APK static (apktool/jadx) + dynamic (Frida/Objection), SSL pinning bypass, root detection bypass, intent fuzzing, keystore extraction, exported components | Android .apk file in scope, Play-Store target, MDM-managed Android device |
Workflow
- Acquire — APK from Play Store (apkpure / apkmirror), MDM extraction (
adb shell pm path <pkg>), or device pull (adb pull) - Static — Pre-pull strings, manifest, permissions; decompile to Java/Smali
- Dynamic — Frida or Objection on a rooted/emulated device; instrument crypto, network, storage
- Network — Burp / mitmproxy with patched APK or Frida SSL-pin bypass
- Backend — The APK is the door — the API behind it is the real attack surface; pivot to
standard/exploit/web/once you have endpoints and tokens
Tooling
| Tool | Use |
|---|---|
apktool |
Smali decompile / recompile / re-sign |
jadx |
Java pseudocode from DEX |
frida / frida-tools |
Runtime instrumentation |
objection |
Frida wrapper — ready-made bypass scripts |
mobsf |
Automated SAST+DAST first-pass triage |
drozer |
IPC / exported-component fuzzer |
apksigner / zipalign |
Re-sign modified APKs for re-install |
frida-ssl-pin-bypass |
Universal SSL-pinning patches |
nox / genymotion / android-studio AVD |
Emulators (x86_64 for speed) |
Decision Notes
- iOS coverage (sub-skill
ios/) is on the roadmap — for iOS work today, leverage the same dynamic patterns (Frida + Objection) and loadandroid/SKILL.mdfor the methodology since the analytical workflow is platform-agnostic. - Mobile backend exploitation almost always pivots to web/API testing — after token extraction, load
/skills/standard/exploit/web/SKILL.md.
What ships with it
1 file 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.
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.
- 9d ago First seen · 48 lines · 39 tokens per session scan A 076b06e2a387
mobile is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 702 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.