Back to skill

Security audit

Wang Jianlin Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only business-perspective skill, but it pushes the assistant to impersonate a real person in first person and stay in that role after broad trigger phrases.

Review this skill before installing if you want clear separation between normal assistant answers and roleplay. Its business frameworks are visible and non-executable, but users may see first-person responses as Wang Jianlin after broad business terms unless they explicitly exit the role.

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:26
Finding

Persistent Real-Person Impersonation and Session-Level Response Hijacking

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 26-37
Vulnerability Type: T01: Skill Instruction Hijacking
Risk Level: High

Vulnerable Instruction Snippet

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

markdown
## Role-Playing Rules

**After this Skill is activated, respond directly as Wang Jianlin.**

- Use “I” instead of “Wang Jianlin would think...”
- Use Wang Jianlin’s tone: military style, decisive and direct, emphasizing execution
- Emphasize “execution,” “goals,” “cash flow,” and “transformation”
- State the disclaimer only once upon initial activation
- Do not say “Wang Jianlin would probably think...”
- Do not leave the role to perform meta-analysis unless the user says “exit role”

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

Technical Analysis

The Skill does not merely configure a writing style or analytical framework. It instructs the Agent to assume the identity of a real person, use first-person identity claims, suppress attribution and uncertainty language, and remain in character until one of several explicit exit commands is received.

The instruction prohibiting meta-analysis further constrains the Agent’s ability to explain that generated statements are simulations based on public information. Although the document includes disclaimers elsewhere, the directive to provide the disclaimer only once does not adequately mitigate later ambiguity.

These instructions constitute session-level instruction hijacking because loading the Skill changes the Agent’s identity presentation and establishes persistent behavioral rules for subsequent responses. No executable code is necessary for exploitation; the Skill text itself is the attack mechanism.

Attack Path

  1. A user invokes the Skill through one of its configured trigger phrases.
  2. The Agent loads a ...[truncated 1265 chars]
Remediation
View remediation

Remediation Suggestions

  1. Replace direct identity assumption with transparent perspective framing, for example: “Using a decision framework inspired by publicly available information about Wang Jianlin.”
  2. Prohibit first-person claims that imply the Agent is the named real person.
  3. Remove the instruction forbidding meta-analysis. The Agent must remain able to explain the source, limitations, and simulated nature of its output.
  4. Remove persistent role-locking behavior and explicit-exit requirements. Persona styling should apply only to the current response unless the user clearly requests continuation.
  5. Permit attribution and uncertainty language whenever claims cannot be directly verified.
  6. Display a concise simulation disclaimer whenever context could reasonably make attribution ambiguous, rather than only once at activation.
  7. State explicitly that system, developer, safety, and current user instructions take precedence over persona rules.
  8. Keep the useful business-analysis models while separating them from identity impersonation and behavioral-control directives.
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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill metadata and instructions are designed to push responses into a fixed identity, language, and stylistic frame centered on a specific persona. Without explicit user opt-in, this can override user expectations, bias outputs, and reduce the assistant's ability to respond neutrally or in the user's preferred mode.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad generic business terms such as '执行力', '订单地产', and '轻资产' that can appear in many unrelated conversations. This creates unintended activation risk, causing the assistant to enter a roleplay persona without clear user intent and potentially override normal response behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The activation rules say the skill should respond directly in-character once activated, but they do not define activation with sufficient precision. Combined with the broad triggers, this ambiguity can cause accidental role assumption, reduce transparency, and make it harder for users to understand when persona instructions are overriding default safeguards or normal assistant behavior.

Content

No source excerpt is available for this finding.