ClawHub
Back to skill

Security audit

Android Studio

Security checks for vulnerabilities and agentic risk

Overview

This Android Studio helper is a benign Markdown-only skill, with a minor privacy consideration because it stores IDE preferences and workflow notes for future use.

Before installing, be aware that the skill may remember Android Studio setup details, project types, pain points, and custom shortcuts. Install it if you want ongoing IDE-specific assistance; decline or clear its memory if you do not want these workflow preferences retained.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The 'When to Use' section says the skill applies whenever a 'User works with Android Studio IDE,' followed by a broad list of common IDE activities. This is ambiguous because it does not define specific invocation phrases, boundaries, or exclusion cases, increasing the chance of unintended activation during ordinary Android development conversations.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The instruction to "Start the conversation naturally" creates an unclear activation boundary for the skill, which can cause the agent to engage or steer the conversation without an explicit user request tied to Android Studio help. In a skills system, ambiguous activation increases the chance of unintended invocation and surprise behavior, even though the content here is not overtly harmful.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to save user-specific preferences, project types, pain points, and custom shortcuts to a persistent memory file without requiring clear notice or consent. This creates a privacy and data-governance risk because the user may not expect their working habits or environment details to be stored across sessions.

Static analysis

No suspicious patterns detected.