Back to skill

Security audit

胡田 OPC导师 任正非 心智模型

Security checks for vulnerabilities and agentic risk

Overview

This skill is a text-only management-advice persona, but it tells the agent to answer in the first person as a real living business figure without requiring clear AI disclosure.

Install only if you specifically want a Chinese-language, Ren Zhengfei-style management simulation. Treat outputs as AI-generated perspective writing, not authentic statements from Ren Zhengfei, and avoid using them where source attribution or public representation of a real person's views matters.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:11
Finding

First-Person Impersonation Through Skill-Level Instruction Hijacking

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill hard-codes a persona and response style that is effectively Chinese-first and does not provide any user language choice or opt-in. This can override the user's preferred language, reduce transparency, and create prompt-control issues where the assistant prioritizes skill instructions over user communication needs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file presents the skill name, description, usage instructions, pricing, and ecosystem information entirely in Chinese. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue, and this README does not indicate that the skill is region-specific or provide an alternative language option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file consists wholly of Chinese-language content and does not provide any opt-in, alternative language, or explanation for a language restriction. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file is natural-language reference content, and the text consistently uses Chinese only from title to footer. Under the policy rule for language or locale violations, forcing a specific language without user opt-in can be a concern when no explicit justification or alternative is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file presents all instructions and content in a single language, Chinese, and does not indicate that users may choose another language or that the file is intended only for a Chinese-language audience. 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.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. This file presents all instructions and content only in Chinese, with no opt-in, alternative language option, or justification that the skill is specifically intended for Chinese-speaking users.

Content

No source excerpt is available for this finding.