Back to skill

Security audit

智能多面手工具箱

Security checks for vulnerabilities and agentic risk

Overview

This is a local Chinese-language utility skill with no evident malicious behavior, but some advertised analysis and quality-check features are only simple canned outputs.

Install only if you are comfortable with a Chinese-language, local utility bundle. Treat the query and quality outputs as lightweight templates or demos rather than verified research, code review, or reliable content-quality scoring.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (11)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire user-facing description and usage examples are presented only in Chinese, including trigger examples and core capability explanations, with no indication that other languages are supported or that the user can opt into Chinese. Under the policy, a skill should not impose a specific language or locale unless it explicitly offers a choice or clearly documents a justified regional scope.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises very broad natural-language trigger phrases such as generic requests for analysis, creativity, and checking quality. Because these phrases overlap heavily with ordinary user conversation, the skill may activate unintentionally or route unrelated requests through its behavior, causing unexpected tool use, confusion, or policy-bypassing workflow changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This code's natural-language descriptions and user-facing output are written only in Chinese, including the main title and runtime status message. Under the policy, forcing a specific language without user choice can be a locale/language policy violation when no opt-in or documented region-specific justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The printed startup message is a user-visible string in Chinese only, and this file contains no mechanism for user language selection or opt-in. That creates a language-policy concern because the skill appears to impose a locale choice by default.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This Python file contains natural-language descriptions entirely in Chinese, including the module title and class docstring, and defines a specific '中文表达优化' dimension. Under the policy, a skill should not impose a specific language or locale without user opt-in or clear justification; no such opt-in or scope limitation is present here.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill claims to perform quality evaluation on supplied content, but the implementation ignores the actual text and returns fixed scores and canned issues. This is dangerous because downstream users or agents may rely on fabricated assessments as if they were real analysis, leading to unsafe automation decisions, false assurance, or misranking of content quality.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains user-facing descriptions, docstrings, and output strings in Chinese only, including the module title and returned suggestion text. Under the language/locale policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is justified, which is not indicated here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains user-facing natural-language text and docstrings exclusively in Chinese, including the skill title and class description. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The process/doc comments describe handling a requested quick tool, implying the code should execute the tool the user asks for. However, in _detect_tool, prompts containing "base64" or "encode" are matched before the later decode branch, so a prompt like "base64 decode" will resolve to base64_encode instead of base64_decode. This is an active contradiction between the stated intent of handling the requested tool and the implemented routing behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code file contains user-facing natural-language text entirely in Chinese in the module docstring, presenting the skill identity and description in a single language. Under the policy, forcing a specific language without offering a choice or documenting a justified locale constraint is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module title and class/docstring text are written entirely in Chinese, and user-facing return strings throughout the file are also Chinese-only. This creates a locale/language constraint without any opt-in or documented choice, which matches the policy rule for forced language behavior.

Content

No source excerpt is available for this finding.