ClawHub
Back to skill

Security audit

App Store Listing Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only prompt pack for generating app store marketing copy and ASO strategy, with no code execution, hidden behavior, credential access, or persistence.

Before publishing generated copy, verify that claims such as user counts, testimonials, competitor comparisons, keyword estimates, notification behavior, and privacy-related descriptions are accurate for your app and compliant with App Store and Google Play policies.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Unbounded Output

Medium
Category
Output Handling
Content
## What This Skill Does

Generates conversion-optimized app store listings for iOS (App Store) and Android (Google Play), plus release notes and an ASO keyword strategy. Every field respects platform character limits — no truncation surprises.

4 prompts covering the full app store presence:
1. **iOS App Store Listing** — Title (30), Subtitle (30), Keywords (100), Description (4,000)
Confidence
60% confidence
Finding
Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Missing User Warnings

Low
Confidence
84% confidence
Finding
At L051, the description says the app learns when users perform habits and uses that history to time nudges. Because this involves monitoring user behavior patterns, the skill description should include some user-facing disclosure about this data use or privacy implications.

Static analysis

No suspicious patterns detected.