Back to skill

Security audit

Guo Guangchang Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language persona/perspective skill for business and investment analysis, with no code execution, credential access, persistence, or hidden data handling found.

Install only if you want a Chinese-language business and investment analysis persona. Treat its outputs as perspective or brainstorming, not verified facts or financial advice; use explicit prompts if you do not want broad business terms to steer the response style.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill definition, examples, and activation guidance are written in Chinese, and there is no statement that users may interact in other languages or opt into Chinese output. For a generally scoped skill, this creates a language/locale policy concern because it appears to impose a specific language by default without user choice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation phrases include broad business terms such as '全球化投资', '产业运营', '并购整合', and '生态协同', which can appear in ordinary user discussions unrelated to roleplay or persona invocation. That increases the chance the skill is triggered unintentionally, causing hidden prompt steering and unexpected behavior changes in contexts where users did not ask for this perspective.

Content

No source excerpt is available for this finding.