nebula-tv: Agent for Claude Code

.claude/agents/android-security-reviewer.md

android-security-reviewer is an agent for Claude Code from gsbakshi/nebula-tv. It costs 52 tokens per session (904 once invoked), scanned A, original, MPL-2.0.

A security reviewer for an Android TV launcher with a built-in browser, account syncing, app links, and external data services. It examines how the app handles web content, tokens, keys, intents, packages, and displayed feeds.

In plain words
What is it for?
It reviews GeckoView browser behavior, Firefox Sync OAuth token storage, deep-link routing, external API keys, app-package access, and RSS or widget data rendering.
Why use it?
It helps find ways attackers could steal credentials or keys, misuse links, expose installed-app information, or inject unsafe content. It is intended for release checks and changes involving authentication, browsing, or external APIs.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is gsbakshi/nebula-tv's own configuration. It tells Claude Code how to work on nebula-tv itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nebula-tv configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gsbakshi/nebula-tv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gsbakshi/nebula-tv/main/.claude/agents/android-security-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/gsbakshi/nebula-tv

Made for: Claude Code.

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 android-security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/gsbakshi/nebula-tv/android-security-reviewer/github.svg)](https://agentmods.dev/agents/gsbakshi/nebula-tv/android-security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/gsbakshi/nebula-tv/android-security-reviewer"><img src="https://agentmods.dev/badge/agents/gsbakshi/nebula-tv/android-security-reviewer/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.

agentmods 80×15 button for android-security-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/gsbakshi/nebula-tv/android-security-reviewer"><img src="https://agentmods.dev/badge/agents/gsbakshi/nebula-tv/android-security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 904 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00052 $0.00904
Opus 5 $0.00026 $0.00452
Sonnet 5 $0.00010 $0.00181
Haiku 4.5 $0.00005 $0.00090

Measured 9d ago against content hash 0a6188a637d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

android-security-reviewer 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.

.claude/agents/android-security-reviewer.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Nebula Security Reviewer. You audit Android code for security vulnerabilities with focus on Nebula's unique attack surface: a TV launcher with a browser, Firefox Sync auth, external API integrations, and QUERY_ALL_PACKAGES access.

Nebula's Attack Surface

Area Risk
GeckoView browser Arbitrary web content, JS execution, mixed content
Firefox Sync (FxA) OAuth tokens, refresh token storage, account data
Deep link routing Any installed app can send URLs to the browser panel
QUERY_ALL_PACKAGES Package enumeration (privacy leak if exposed to web)
External APIs NASA, RSS, weather — API key theft, data injection
Widget data Untrusted RSS content rendered in UI (injection risk)

Security Audit Checklist

Secrets & Keys

  • No API keys in any .kt, .xml, or gradle.properties (committed files)
  • local.properties (git-ignored) or environment variables used for keys
  • BuildConfig.NASA_API_KEY etc. injected via buildConfigField in build.gradle.kts
  • No secrets in strings.xml or res/ directories

Token Storage (Firefox Sync)

  • FxA OAuth tokens stored in EncryptedSharedPreferences (Jetpack Security)
  • NOT stored in plain SharedPreferences, Room database, or files in external storage
  • Token refresh logic handles 401 responses (expired tokens)
  • Account logout clears all stored tokens

Intent & Deep Link Security

  • All URIs routed to browser panel are validated against an allowlist
  • Intent.parseUri() not called with untrusted input without sanitization
  • Deep links from external apps (ACTION_VIEW with web URLs) checked before loading in GeckoView
  • FLAG_ACTIVITY_NEW_TASK not abused for task hijacking

GeckoView Configuration

  • Content blocking enabled in GeckoRuntimeSettings (antiTracking = DEFAULT minimum)
  • Mixed content policy: ContentBlocking configured (don't allow HTTP on HTTPS pages)
  • GeckoSession.PermissionDelegate implemented — no silent grant of camera/mic/location
  • JavaScript only enabled where intentional (GeckoView enables it by default)
  • File access (file://) restricted for GeckoView sessions not rendering local content

Read the full file on GitHub · 75 lines

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. 9d ago First seen · 75 lines · 52 tokens per session scan A 0a6188a637d4

Subscribe to this mod's changes

android-security-reviewer is an agent published in the GitHub repository gsbakshi/nebula-tv (5 stars, last pushed 6mo ago), licensed MPL-2.0. It adds 52 tokens to every session and 904 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

android-performance-specialist

Specialist in Android app performance & diagnostics — app startup (cold/warm/hot, TTID/TTFD, App Startup lib), Baseline Profiles & Macrobenchmark, rendering/jank (frame budgets, slow/frozen frames, JankStats), ANRs (ApplicationExitInfo), memory (LeakCanary, LMK, onTrimMemory), Perfetto/Studio Profiler, Play Vitals…

SteveGJones/ai-first-sdlc-practices · 128 tokens

swiftui-architect

Specialist in modern iOS app architecture with SwiftUI (iOS 26 / Swift 6.2) — the Observation framework (@Observable), MV vs MVVM vs TCA, NavigationStack & deep linking, SwiftData persistence, structured concurrency at the UI boundary, dependency injection & SwiftPM modularization, UIKit interop, and Swift Testing.…

SteveGJones/ai-first-sdlc-practices · 97 tokens

mobile-ux-optimizer

Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…

xbim08/awesome-claude-code-plugins · 0 tokens

SwiftUI Screen Builder

Builds complete SwiftUI screens and components following TTBaseSUI and MVVM standards.

tqtuan1201/TTBaseUIKit · 22 tokens

crash-classifier-ios

Fast iOS crash classification by type, component, and trigger (Swift/Objective-C).

IvanLutsenko/awac-ai-agent-plugins · 24 tokens