Security audit

YZTurboWebAndroid

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Android WebView integration skill whose behavior is coherent, but users should add normal WebView and JS bridge security checks before using the examples in production.

Before installing, treat this as an Android WebView integration guide. If you copy the JS Bridge pattern, restrict handlers to trusted pages or origins, authenticate and authorize sensitive calls, expose only the minimum user data needed, and review the referenced Gradle dependency according to your app's normal supply-chain process.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The JS Bridge example shows native code returning user information directly to web content without any origin validation, authentication check, consent flow, or data-minimization guidance. In a WebView/JS-bridge context, exposing account or profile data to loaded H5 pages is security-sensitive because any trusted-but-compromised page, XSS on the page, or overly broad bridge availability could let web content access native-held user data.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: The natural-language instructions and examples are presented only in Chinese, which can function as an implicit language constraint. The file does not indicate that the skill is region-specific or offer an alternative language, so it may violate a language/locale policy requiring user choice or explicit justification.

Static analysis

No suspicious patterns detected.