Back to skill

Security audit

AI 工作流优化专家

Security checks for vulnerabilities and agentic risk

Overview

This is a static Chinese-language AI workflow advice skill with no executable code, persistence, credential access, or hidden behavior.

Before installing, expect this skill to provide Chinese-language guidance about prompts, AI tool choice, and workflow optimization. It includes the author’s custom-service contact information, but it does not execute code or access local data.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
92% confidence
Finding

The skill description is broad enough to match many generic requests about AI assistance, tool selection, and workflow help. Overly broad invocation criteria can cause the skill to activate outside its intended scope, leading to prompt hijacking of unrelated conversations, user confusion, or unrequested steering toward this skill’s guidance and embedded promotion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill includes an instruction to write in Chinese without indicating that this is conditional on user preference. Forced language output can override the user’s requested language or system behavior, reducing reliability and potentially causing miscommunication in downstream workflows that expect another language.

Content

No source excerpt is available for this finding.