ClawHub
Back to skill

Security audit

Android Cli

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward Android CLI reference skill whose device, SDK, screenshot, and project-management commands are disclosed and fit its stated Android development purpose.

Install this skill only if you want agents to use Android CLI and adb workflows. Review commands before allowing SDK installs, removals, CLI updates, emulator deletion, APK deployment, adb input, or skill add/remove actions, and avoid saving or sharing screenshots or layout dumps from screens that contain secrets or private data.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly instructs users to install, update, and remove SDK packages, which are system-modifying operations, but provides no caution about side effects such as altering toolchains, breaking builds, changing versions, or removing required components. In an agent setting, documentation that normalizes these actions without confirmation or safety guidance increases the risk of unintended environment changes and supply-chain exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill tells users to capture screenshots to a file without warning that screenshots may contain sensitive information such as credentials, personal data, API keys, or proprietary app content. In agent-driven workflows, this can lead to accidental persistence or exfiltration of confidential device screen contents.

Content

No source excerpt is available for this finding.