鬼谷子智慧

• Outcome: Pass
• Latest audit: May 31, 2026, 3:38 AM
• Version:
  1.0.0

Overview

This is a text-only Chinese strategy and persuasion skill with no code or data access, but users should apply its influence tactics carefully.

Install only if you want Guiguzi-style negotiation and strategy guidance. Treat advice about probing, leverage, concealment, or control as material for ethical negotiation, historical study, or defensive awareness, not coercion, fraud, harassment, or manipulation of unwilling people.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger list consists of broad, generic terms such as '谈判', '说服', and '谋略', which are likely to appear in many ordinary user requests. This can cause the skill to activate outside narrowly intended contexts and inject manipulative guidance into benign conversations, increasing the chance of inappropriate or unsafe assistance.

Natural-Language Policy Violations

Medium

• Confidence: 97% confidence
• Finding: The skill repeatedly teaches covert influence and manipulative persuasion techniques, including hiding intent, probing weaknesses, exploiting gaps, and making others believe an idea is their own. Without explicit consent boundaries, ethical constraints, or disallowed-use limits, this materially increases the risk of enabling deception, coercion, and social-engineering style misuse.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 84% confidence
• Finding: The trigger '谈判' is extremely short and semantically broad, so it may match many routine requests involving negotiation advice. In this skill's context, accidental activation is more concerning because the content emphasizes strategic manipulation rather than neutral negotiation support.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 84% confidence
• Finding: The trigger '说服' is a common word that can appear in many harmless contexts, making unintentional activation likely. Because the skill includes tactics for steering, testing, and controlling others, even incidental matching could surface manipulative advice where the user did not request it.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 82% confidence
• Finding: The trigger '游说' is short and generic enough to match normal discussion of lobbying or persuasion. Given the skill's emphasis on influence operations and strategic probing, accidental activation can expose users to higher-risk manipulative guidance than expected.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 81% confidence
• Finding: The trigger '谋略' is a broad concept that appears across many strategic or historical discussions. In a skill that contains advice on concealment, leverage, and exploiting counterpart weaknesses, broad matching raises the risk of over-triggering manipulative content.

Overly Broad Trigger

Low

• Category: Trigger Abuse
• Confidence: 79% confidence
• Finding: The trigger '纵横' is concise and ambiguous, and may be used in literary, historical, or general strategic contexts unrelated to this skill. Because the skill operationalizes influence and control techniques, unintended activation can introduce risky content into unrelated conversations.

VirusTotal

64/64 vendors flagged this skill as clean.