Back to skill

Security audit

Houwei Hello World

Security checks for vulnerabilities and agentic risk

Overview

This is a simple sync-test skill that only returns a disclosed confirmation message and does not request sensitive access or run code.

Installers should understand that saying one of the trigger phrases may cause a simple confirmation reply that includes the current device name. There is no evidence of hidden execution, data collection, credential use, or persistence.

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
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 (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger keyword "我的技能" is generic and could plausibly appear in ordinary conversation about a user's skills or custom tools. The file does not provide constraints, negative examples, or narrower activation context to distinguish intentional invocation from casual mention.

Content

No source excerpt is available for this finding.