ClawHub
Back to skill

Security audit

HarmonyOS NEXT Expert

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-navigation skill for HarmonyOS NEXT, and the reviewed artifacts do not show hidden execution, persistence, credential use, or destructive behavior.

Install this if you want HarmonyOS NEXT/ArkTS reference help from a local documentation index. The main practical limitation is that much of the reference material is in Chinese, so users needing English-only guidance may get less usable answers.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Content
JsEtsAPIReference/@ohos.app.ability.wantConstant (Want常量).md
JsEtsAPIReference/@ohos.app.appstartup.StartupConfig (启动框架配置信息).md
JsEtsAPIReference/@ohos.app.appstartup.StartupConfigEntry (启动框架配置).md
JsEtsAPIReference/@ohos.app.appstartup.StartupListener (启动框架任务监听器).md
JsEtsAPIReference/@ohos.app.appstartup.startupManager (启动框架管理能力).md
JsEtsAPIReference/@ohos.app.appstartup.StartupTask (启动框架任务).md
JsEtsAPIReference/@ohos.app.form.formBindingData (卡片数据绑定类).md
Confidence
75% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The directive 'Always use the declarative UI paradigm syntax' mandates one development style categorically. This is a natural-language policy concern because it removes user choice and is phrased as a blanket requirement rather than a context-specific recommendation.

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
This markdown index is entirely presented using Chinese-language titles and labels, with no indication that the locale is optional or that the skill is intentionally region-specific. Under the policy rule for language/locale constraints, a file that effectively forces one language without opt-in can be considered a natural-language policy issue.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
This markdown index lists kit names and descriptions predominantly in Chinese, which can impose a specific language on users without opt-in. The file does not indicate that it is intentionally region-specific or provide an alternative language path.

Static analysis

No suspicious patterns detected.