ClawHub
Back to skill

Security audit

Android开发专用

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a plain Android development helper, but it explicitly offers permission bypass and hidden API invocation guidance without clear authorized-use limits.

Review carefully before installing. This skill may be useful for Android system or AOSP engineers, but its permission-bypass and hidden-API guidance should only be used in authorized development, testing, or compatibility work and should favor documented Android APIs and proper permission flows where possible.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (4)

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly advertises help with hidden API access and 'permission bypass', which directly enables evasion of Android platform security controls. In the context of an agent skill that promises executable guidance and code, this materially increases the risk that users receive instructions to circumvent OS restrictions, violate app store/device policy, or facilitate unauthorized access.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

Listing '权限绕过' as a core capability normalizes and endorses bypassing Android's permission model, a fundamental security boundary. Because the skill is framed as a practical engineering assistant that provides direct commands and code, this is not merely descriptive context; it signals operational support for misuse.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is written entirely as first-person operating instructions in Chinese and does not indicate that users may choose another language or locale. Under the policy, a skill that effectively imposes a specific language without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example promises directly usable reflection code to invoke hidden system APIs, without any compliance, authorization, or safety limitations. In Android, reflective hidden-API invocation is commonly used to evade platform restrictions, so providing turnkey guidance lowers the barrier to abuse even if the stated use case is development-related.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.