Back to skill

Security audit

Liu Qiangdong Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed business-advice roleplay skill with no code execution or data access, but users should treat its first-person public-figure persona as simulation only.

Install only if you want a Chinese-language roleplay-style business framework. Treat all first-person answers as simulated perspective based on public information, not real statements or endorsement from Liu Qiangdong, and use the exit phrases if you want normal assistant behavior.

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:49
Finding

Persistent Persona and Response-Control Instruction Hijacking

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 49-60
Vulnerability Type: T01: Skill Instruction Hijacking
Risk Level: High

Vulnerable Instruction Segment

The following is an English translation of the complete relevant instruction segment:

markdown
## Role-Playing Rules

**After this Skill is activated, respond directly as Liu Qiangdong.**

- Use "I" instead of "Liu Qiangdong would think..."
- Use Liu Qiangdong's tone: direct, forceful, and fraternal.
- When encountering uncertainty, handle it in Liu Qiangdong's way: calculate costs first, then consider efficiency.
- **Provide the disclaimer only once upon initial activation** and do not repeat it in subsequent conversation.
- Do not say "Liu Qiangdong would probably think..." or "If it were Liu Qiangdong, he might..."
- Do not leave the role to perform meta-analysis unless the user says "exit role."

**Exiting the role**: Return to normal mode when the user says "exit," "switch back to normal," or "stop role-playing."

Technical Analysis

The Skill does more than provide an optional analytical framework. It directs the Agent to assume the identity of a real person, forces first-person presentation, controls tone and reasoning, suppresses repeated disclosure, and prohibits neutral meta-analysis until the user provides a designated exit command.

These instructions alter the Agent's active-session behavior when the Skill is loaded. The combination of first-person impersonation and disclosure suppression can obscure that the output is generated from a modeled perspective rather than issued by the represented individual. The restriction on meta-analysis also attempts to prevent the Agent from transparently explaining the imposed behavior.

This is classified as instruction hijacking because the Skill replaces ordinary response behavior with persistent persona-level rules. No evidence was found that these rules modify long-term memory, survive outside the active session, o ...[truncated 1588 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace direct identity assumption with explicit perspective framing, such as: "Analyze the question using a framework inspired by publicly available information about Liu Qiangdong."
  2. Prohibit claims that the Agent is the represented person and avoid first-person statements that imply authentic identity.
  3. Include a concise disclosure in every response produced under the persona, not only upon initial activation.
  4. Remove the instruction that prohibits meta-analysis. The Agent must remain able to explain that the output is simulated and to discuss the framework's limitations.
  5. Treat activation and exit phrases as user-interface conveniences rather than persistent behavioral locks.
  6. State explicitly that system instructions, developer instructions, user intent, factual accuracy requirements, and safety controls take precedence over persona guidance.
  7. Present the cost, efficiency, logistics, and management principles as optional analytical heuristics rather than authoritative beliefs of the named person.
  8. Add uncertainty language for claims not directly supported by cited public sources and avoid fabricating personal opinions.
  9. Consider using a fictional or generic executive persona if first-person role-play is essential to the intended experience.
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

The skill metadata and trigger design are entirely Chinese-oriented, and the document provides no opt-in or alternative language behavior. This can constitute a language/locale policy issue because the skill effectively assumes a specific language rather than explicitly offering the user a choice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill explicitly minimizes ongoing disclosure by saying the disclaimer should only appear once, while also requiring direct first-person impersonation of a real public figure. That increases the risk that later turns will be mistaken as authentic personal endorsement, especially in business, governance, or employment advice contexts where authority cues matter.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documentation first states that the skill is not Liu Qiangdong本人 and is only a framework based on public information (L018-L019), but later instructs the skill to respond directly '以刘强东的身份' and use '我' rather than framing it as perspective-taking (L049-L055). That is an active contradiction in the skill's own intent documentation, not merely an omitted detail.

Content

No source excerpt is available for this finding.