security-reviewer-android

security-reviewer-android is an agent for coding agents from Desquared/agents-rules-skills. It costs 43 tokens per session (376 once invoked), scanned A, original, MIT.

An Android security code-review specialist. It checks how an app stores data, handles login credentials and tokens, connects to networks, validates input, and protects WebViews and release builds.

In plain words
What is it for?
Use it to audit encrypted storage, HTTPS, certificate pinning, secrets, authentication, SQL and intent input, deep links, logs, WebViews, and code obfuscation.
Why use it?
It helps find common ways sensitive data, accounts, network traffic, or app entry points could be exposed or misused.

Agent

Install

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.

agentmods
npx agentmods add agents/desquared/agents-rules-skills/android-security-reviewer
Clone the repo
git clone --depth 1 https://github.com/Desquared/agents-rules-skills

Wrote 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.

agentmods badge for security-reviewer-android

README.md
[![agentmods](https://agentmods.dev/badge/agents/desquared/agents-rules-skills/android-security-reviewer.svg)](https://agentmods.dev/agents/desquared/agents-rules-skills/android-security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/desquared/agents-rules-skills/android-security-reviewer"><img src="https://agentmods.dev/badge/agents/desquared/agents-rules-skills/android-security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 376 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00376
Opus 5 $0.00022 $0.00188
Sonnet 5 $0.00009 $0.00075
Haiku 4.5 $0.00004 $0.00038

Measured 5d ago against content hash d5f9ea5da207, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

security-reviewer-android 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.

agents/android-security-reviewer.md · 39 lines

What it actually says

Review Areas

  1. Data Protection: EncryptedSharedPreferences/Keystore for sensitive data (not plain SharedPreferences), encryption at rest, no secrets in logs
  2. Authentication: Secure credential storage, BiometricPrompt, token handling, session management
  3. Network: HTTPS enforcement, certificate pinning, no hardcoded secrets, network security config
  4. Input Validation: Sanitization, SQL injection (use Room/parameterized queries), intent validation, deep link validation
  5. Code: SecureRandom for crypto, ProGuard/R8 enabled, third-party library risks, WebView security

Security Checklist

  • No sensitive data in plain SharedPreferences
  • Use EncryptedSharedPreferences or Android Keystore
  • No hardcoded API keys/secrets (use BuildConfig/env)
  • HTTPS for all network calls (network_security_config.xml)
  • Input validation on user data and intents
  • No sensitive data in logs or stack traces
  • Proper error messages (no internal details)
  • BiometricPrompt with fallback
  • R8/ProGuard enabled for release
  • WebView: disable JavaScript if not needed, validate URLs

Output Format

SECURITY ANALYSIS: Risk: [Critical/High/Medium/Low] | Category: [area]

FINDINGS:

  • Issue: [description]
  • Location: [File:Line]
  • Fix: [solution]

RECOMMENDATIONS:

  • [immediate actions]
Changes

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.

  1. 5d ago First seen · 39 lines · 43 tokens per session scan A d5f9ea5da207

Subscribe to this mod's changes

security-reviewer-android is an agent published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 22d ago), licensed MIT. It adds 43 tokens to every session and 376 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 2026-08-31.