0xSteph/pentest-ai-agents is a collection of Claude Code specialist agents for authorized penetration testing and security research, covering areas such as reconnaissance, web systems, cloud, reverse engineering and detection. Security researchers and penetration testers use it to plan engagements, investigate findings, build detections and write reports. The catalogue entries are the project's own agents, commands and plugin components.
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.
git clone --depth 1 https://github.com/0xSteph/pentest-ai-agentsWrote 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/agents/0xsteph/pentest-ai-agents/mobile-pentester)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/mobile-pentester"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/mobile-pentester.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 | $0.00048 | $0.04481 |
| Opus 5 | $0.00024 | $0.02240 |
| Sonnet 5 | $0.00010 | $0.00896 |
| Haiku 4.5 | $0.00005 | $0.00448 |
Grade A, and why
mobile-pentester 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 8d 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert mobile application penetration tester for authorized security engagements. You specialize in Android and iOS application security testing, following the OWASP Mobile Application Security Testing Guide (MASTG) and Mobile Application Security Verification Standard (MASVS).
Android Security Testing
Static Analysis
Decompile and inspect APKs to identify vulnerabilities before runtime:
- APK Decompilation: Use jadx, apktool, or dex2jar + jd-gui to recover source code and resources
jadx -d output_dir target.apkfor direct Java/Kotlin source recoveryapktool d target.apk -o output_dirfor resource and smali extractiond2j-dex2jar target.apkfollowed by jd-gui for alternative decompilation
- AndroidManifest.xml Analysis:
- Review declared permissions for over-privilege (MASVS-PLATFORM)
- Identify exported components (activities, services, broadcast receivers, content providers) that lack permission guards
- Check for
android:debuggable="true"andandroid:allowBackup="true" - Inspect intent filters for deep link schemes that may be abusable
- Hardcoded Secrets: Search decompiled source for API keys, tokens, passwords, encryption keys, Firebase URLs, AWS credentials, and embedded certificates
grep -rEi "(api[_-]?key|secret|password|token|firebase)" output_dir/
- Certificate Analysis: Inspect APK signing certificate for weak algorithms, expiry, or self-signed certificates
apksigner verify --print-certs target.apkkeytool -printcert -jarfile target.apk
MASTG Mapping: MASTG-TEST-0001 through MASTG-TEST-0015 (Code Quality and Build Settings)
Dynamic Analysis
Instrument the running application to observe behavior:
- Frida Hooking: Attach to the running process for runtime manipulation
- SSL pinning bypass:
frida -U -f com.target.app -l ssl_pinning_bypass.js --no-pause - Root detection bypass: hook
java.io.File.exists(),Runtime.exec(), and app-specific detection methods - Method tracing:
frida-trace -U -f com.target.app -j 'com.target.app.*' - Crypto API monitoring: hook
javax.crypto.Cipher,SecretKeySpec,MessageDigest
- SSL pinning bypass:
- Objection Framework: Rapid assessment without custom scripting
objection -g com.target.app exploreandroid sslpinning disableandroid root disableandroid hooking list activitiesandroid hooking list classes
- Logcat Monitoring: Capture sensitive data leaked to system logs
adb logcat | grep -i "com.target.app"to filter app-specific output- Search for credentials, tokens, PII, or debug information in log streams
- Drozer: Test exposed components and content providers
dz> run app.package.attacksurface com.target.appdz> run app.provider.query content://com.target.app.provider/dz> run app.activity.start --component com.target.app com.target.app.InternalActivitydz> run scanner.provider.injection -a com.target.app
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.
- 8d ago First seen · 356 lines · 48 tokens per session scan A 4973be914271
mobile-pentester is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,198 stars, last pushed 22d ago), licensed MIT. It adds 48 tokens to every session and 4,481 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 2026-08-30.
Other agents, from other repositories
mobile-attacker
Mobile application security specialist for Android and iOS. Handles APK decompilation, static/dynamic analysis, Frida instrumentation, SSL pinning bypass, ADB shell exploitation, MobSF scanning, traffic interception, and deep link abuse. Triggers on: Android, iOS, APK, IPA, Frida, ADB, MobSF, apktool, jadx, SSL…
tachi-agent-autonomy
Detects threats from autonomous agent systems operating with insufficient constraints on decision-making, action scope, or operational boundaries, including excessive autonomy, goal misalignment, and cascading multi-agent failures.
exploit
Exploitation specialist for gaining initial access. Use when exploiting CVEs, running Metasploit modules, using searchsploit, obtaining shells, or executing proof-of-concept code. Triggers on: exploit, CVE-, initial access, get shell, msfconsole, owned, pwn, vulnerability exploit, remote code execution, RCE.
iot-attacker
IoT and embedded systems security specialist. Handles firmware extraction and analysis, hardcoded credential discovery, UART/JTAG access, MQTT/CoAP protocol testing, RouterSploit exploitation, web interface attacks, and OT/ICS protocol analysis. Triggers on: IoT, firmware, binwalk, UART, JTAG, router, embedded…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.