Back to skill

Security audit

AI Automation Workflow

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language workflow-design guide and it does not ask for code execution, credentials, persistence, or sensitive access.

Install this if you want Chinese-language guidance for designing business automation workflows. Be aware that generic trigger words may activate it in adjacent workflow discussions, and non-Chinese users may need translation or language preference handling.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords are very broad and include common terms like '自動化', 'workflow', and 'AI agent', which can cause the skill to activate on many unrelated user requests. Over-broad activation can route users into unintended behavior, reduce system predictability, and increase the chance that the skill intercepts prompts outside its intended scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill metadata and content are written in Traditional Chinese and present the skill as operating in that locale without any indication of user choice. Forcing a language or locale without opt-in can degrade user comprehension, cause incorrect interpretation of business or technical requirements, and create unsafe mismatches in multilingual environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.