Back to skill

Security audit

Ren Zhengfei Perspective

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language business-perspective skill that provides Ren Zhengfei-style analysis without code execution, persistence, credential use, or data access.

Install this if you want business advice framed through Ren Zhengfei and Huawei management concepts. Be aware it may activate on some broad business prompts and may answer with a strong, Chinese-language persona-specific framing, so users who want neutral or multilingual advice should invoke it deliberately or disable it for general business questions.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill defines activation using broad business prompts like '这个商业模式有护城河吗' and '从长期主义想想' even when the user does not explicitly request the Ren Zhengfei persona. This can cause unintended persona hijacking, where normal business queries are silently redirected into a specific ideological framework, reducing user control and potentially biasing advice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The '何时激活' section uses broad topical categories such as strategy, crisis management, innovation, organization, customer relations, and competition as activation conditions. Because these are common business subjects, the skill may over-activate on ordinary requests and inject a strong persona-specific framing without clear user consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file’s title and all substantive content are in Chinese, and there is no indication that users can choose another language or that the document is intentionally limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The document title and all substantive content are written entirely in Chinese, with no indication that language selection is optional or that the file is intentionally limited to a Chinese-speaking context. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file presents all instructions and content exclusively in Chinese, and it does not indicate that the user can choose another language or locale. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a reportable issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.