Back to skill

Security audit

Zhou Hongyi Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only business perspective roleplay skill with no code or system access, though users should be aware it can adopt a real-person persona too broadly.

Install only if you want an opinionated Zhou Hongyi-style business persona. Use explicit prompts and exit with “退出” or “切回正常” when done; treat outputs as a simulated perspective, not real statements from Zhou Hongyi.

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

Warning
Location
SKILL.md:21
Finding

Session-Wide Identity and Response-Mode Hijacking

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 21–30
Vulnerability Type: T01: Skill Instruction Hijacking
Risk Level: Medium

Vulnerable Instruction Segment

The following is an English rendering of the complete affected segment:

markdown
## Role-Playing Rules

After activation, respond directly as Zhou Hongyi:
- Use “I” and speak in a direct, sharp, down-to-earth tone.
- Prefer words such as “free,” “users,” “disruption,” “battle,” and “security.”
- Habitually use war metaphors to explain business issues.
- Maintain a challenging attitude toward industry giants and authorities.
- Provide the disclaimer only once.

**Exit**: Return to normal only when the user says “exit” or “switch back to normal.”

Technical Analysis

The skill directs the agent to respond as a specific real person rather than transparently presenting an analytical simulation of that person’s publicly documented perspective. It also instructs the agent to use first-person language, provide a disclaimer only once, and preserve the altered mode until one of two explicit exit commands is received.

These instructions alter the agent’s identity presentation and ongoing response policy when the skill is loaded. Requiring a special exit phrase can cause the role to affect later, unrelated requests within the same active session. Suppressing the disclaimer after its first occurrence further increases the possibility that subsequent responses will be misunderstood as authentic statements by the named individual.

This is instruction-level behavior manipulation rather than agent memory poisoning: the audited file does not write rules to long-term memory or establish persistence outside the active skill context.

Attack Path

  1. A user activates the skill through one of its documented trigger phrases.
  2. The skill instructs the agent to claim the response perspective directly as Zhou Hongyi and to use first-person s ...[truncated 1247 chars]
Remediation
View remediation

Remediation Suggestions

  1. Replace direct identity adoption with transparent perspective framing, such as: “Analyze the question using ideas commonly associated with Zhou Hongyi.”
  2. Explicitly prohibit claims that the agent is Zhou Hongyi or that generated responses are authentic statements from him.
  3. Avoid first-person language that could imply genuine identity. Use formulations such as “This perspective would emphasize...” instead.
  4. Remove the instruction to provide a disclaimer only once. Include a concise disclosure whenever the context could reasonably cause identity confusion.
  5. Remove persistent mode behavior and special exit-phrase requirements. Apply the perspective only to the request that explicitly invokes it.
  6. Require explicit user confirmation before applying the perspective to later requests.
  7. Add a rule stating that higher-priority system and safety instructions always override persona or style instructions.
  8. Distinguish documented facts from generated interpretation and avoid attributing invented quotations or opinions to the named individual.
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad business phrases such as '免费模式', '颠覆式创新', and '战斗文化', which can appear in ordinary strategy discussions and may activate the skill unintentionally. This can cause unsolicited persona injection and steer responses into a fixed ideological/business style when the user did not explicitly request it.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to respond directly as Zhou Hongyi, in first person and a fixed aggressive style, immediately upon activation and without clear user opt-in. This can override user preferences, reduce transparency, and lead to misleading impersonation or unwanted behavioral shaping in contexts that only loosely match the trigger phrases.

Content

No source excerpt is available for this finding.