ClawHub
Back to skill

Security audit

Yiri App Version Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow app-version checker that launches a browser to read a fixed Huawei AppGallery page, with no evidence of hidden access, persistence, credential use, or destructive behavior.

Before installing, expect this skill to use Playwright/Chromium and make a network request to Huawei AppGallery when version-related Chinese queries for 一日记账 are detected. Consider tightening the broad app-name trigger if accidental browser launches would be a concern.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger keywords are broad enough that the skill may activate on generic mentions like '一日记账 app', not just explicit version-check requests. That can cause unintended browser automation and external network access, which increases the chance of surprising behavior, unnecessary resource use, and accidental invocation in unrelated conversations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The module docstring is written entirely in Chinese and indicates the skill is specifically for querying the app version, with no indication that users can choose another language or locale. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.