Back to skill

Security audit

He Xiangjian Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language business-perspective roleplay skill with no code execution, credential access, persistence, or hidden data flows.

Install this if you want a Chinese-language simulated business-management perspective. Be aware that generic terms like “职业经理人” or “稳健经营” may activate the skill unintentionally, and treat any first-person output as roleplay based on public information rather than real advice from He Xiangjian.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger list contains broad business phrases such as “放权授权”, “职业经理人”, and “稳健经营” that can appear in normal enterprise discussions without an explicit request to activate the skill. This creates a prompt-routing risk where the persona may activate unintentionally and steer responses into a fixed perspective, reducing user control and causing misleading or irrelevant outputs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill specifies that, once activated, it will respond in a fixed first-person Chinese persona and style without offering language choice or consent. This can override user preferences, create confusion about whether the model is roleplaying, and increase the chance of inappropriate persona persistence across unrelated requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file presents all user-facing instructions and test descriptions exclusively in Chinese. Under the policy, forcing a specific language without user opt-in or documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.