Back to skill

Security audit

Wukong — 名人思维蒸馏框架(72变版)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language persona-thinking framework that saves generated persona templates locally, with no evidence of hidden code execution, network access, credential use, or destructive behavior.

Install this if you want a Chinese-language framework for saving and reusing persona-style thinking models. Be aware that new distillations may be written into local Markdown files, so avoid using sensitive private details in prompts you do not want persisted.

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
  • 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 (9)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list is very broad and includes common conversational phrases such as 'Think Like', '像XX一样', and 'XX会怎么做', which can cause the skill to activate in contexts where the user did not intend to invoke it. In an agent system, unintended activation can lead to irrelevant persona-driven outputs and may cascade into unintended file reads/writes because this skill also defines persistence behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to save generated persona content into wukong/personas/ and update wukong/registry.md, but it provides no user warning, consent step, or retention policy. Persistent writes create privacy and integrity risks because user-driven prompts may be stored unexpectedly, and repeated unintended activations could accumulate unreviewed or misleading artifacts on disk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown template forces a specific language/locale for all users through its headings and instructions. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific; neither is present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This file presents all user-facing guidance in Chinese and does not mention that the language is optional or configurable. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The usage section defines activation patterns like '用[人物名]思维分析[你的问题]' and '蒸馏[人物名]的[什么领域]思维' without boundaries, exclusions, or narrowing context. These patterns are generic enough to overlap with ordinary requests and do not clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file states that distillation will automatically save output into the personas/ directory without mentioning any user confirmation or safeguards around file creation/modification. In an agent setting, undocumented automatic writes can lead to unintended persistence, overwriting files, or creating attacker-influenced content that later gets trusted or invoked.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The entire skill manifest and operating instructions are written in Chinese, and the examples and trigger phrases assume Chinese usage, with only limited embedded English phrases. There is no statement that users may choose another language or that the locale is intentionally limited to a Chinese-only context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The file presents all instructions and usage guidance in Chinese, which can effectively force a specific language for users of the skill. Under the policy criteria, language constraints should either be optional for the user or clearly documented as region-specific and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The file presents '触发词示例' with several examples, but only examples are given and no explicit statement says whether these are exhaustive or what variants are accepted. This can leave activation behavior ambiguous and increase the risk of unintended invocation.

Content

No source excerpt is available for this finding.