Back to skill

Security audit

鬼谷子智慧

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only strategy and persuasion coaching skill with visible ethical cautions and no code, tools, persistence, or data access, though its persuasion framing could be misused.

Install this only if you want a Chinese/English Guiguzi-style negotiation and persuasion coach. Use it for transparent, lawful negotiation or strategy planning, and avoid applying it to deception, coercion, intimate relationships, political manipulation, or exploiting vulnerable people.

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
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 (14)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger set is broad and overlaps with ordinary discussion of negotiation, persuasion, and strategy, which can cause the skill to activate in contexts where the user did not specifically request this manipulative-strategy persona. Unintended activation matters here because the skill provides tactics for probing, influencing, and exploiting interpersonal weaknesses, so accidental invocation can steer conversations toward coercive framing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This section operationalizes manipulative tactics such as praise-then-control, probing emotional weaknesses, and exploiting fissures in alliances, while the policy framing is too weak to prevent harmful use. In context, the skill is explicitly designed for persuasion, lobbying, and interpersonal games, which increases the likelihood that users apply it to coercion, deception, workplace abuse, or targeted social engineering.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The file presents the skill primarily in Chinese throughout its title, descriptions, scenarios, and lookup table, with only limited English glosses in section headers. Because there is no statement offering language choice or explaining that the skill is intended only for Chinese-speaking users or a region-specific audience, it creates a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire template is written in Chinese and includes no note that the skill is China-specific or that users may choose another language. Under the policy rule, a skill that effectively mandates a specific language without opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file contains user-facing instructional text primarily in Chinese while also forcing English phrasing such as 'Mind-Reading Step-by-Step Template' and 'legacy'. Under the language/locale policy, presenting a fixed language mix without offering the user a choice can be a natural-language policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The document is written entirely in Chinese and presents itself as a general-purpose persuasion template, but it does not state that Chinese is optional or that the skill is intended only for a Chinese-speaking context. Under the language/locale policy criterion, a skill that effectively requires a specific language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.