Back to skill

Security audit

Xu Jiayin Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language business-case persona skill for studying Xu Jiayin/Evergrande as a cautionary example, with no executable code, persistence, credential use, or data access.

Install only if you want a Chinese-language cautionary business-analysis persona. Be aware that generic terms like high leverage or diversification may trigger it unexpectedly, and treat its business framing as historical risk analysis rather than operational advice.

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
93% confidence
Finding

The trigger list contains generic business terms such as “规模至上”, “高杠杆”, and “多元化” that can appear in ordinary strategy or finance discussions unrelated to this persona. That creates unintended activation risk: the system may switch into a Xu Jiayin role unexpectedly, introducing a high-risk expansion persona into benign contexts and potentially shaping advice in ways the user did not request, even though the skill includes warnings.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill description and all operational instructions are written entirely in Chinese, and the file does not state that users may choose another language or that the Chinese-only constraint is intentional and justified. Under the language/locale policy, a skill should not implicitly force a specific language without opt-in or a documented rationale.

Content

No source excerpt is available for this finding.