Back to skill

Security audit

Yu Minhong Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a plain markdown perspective skill for Yu Minhong-style education and entrepreneurship advice, with only a minor chance of activating on broad related phrases.

Before installing, consider whether you want general education-transformation discussions to invoke this viewpoint. The skill appears text-only and purpose-aligned, but narrower trigger phrases would make activation more predictable.

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

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes several broad phrases such as “教育转型”, “新东方思维”, and “俞敏洪模式” that may match ordinary discussion topics rather than an explicit request to invoke this skill. This can cause unintended activation, leading to irrelevant persona injection or unexpected behavior in contexts where the user did not clearly ask for this specific framework.

Content

No source excerpt is available for this finding.