ClawHub
Back to skill

Security audit

中文内容精修助手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese text-polishing skill with no executable code, network behavior, persistence, or hidden data handling, though users should avoid using it to misrepresent authorship.

Install only if you want Chinese-language rewriting and platform formatting. Do not use the skill where AI-use disclosure, academic honesty, workplace policy, or platform rules require transparent attribution.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README explicitly markets the skill as helping users 'hide the AI tail' and make AI-generated text appear human-authored, but provides no warning about deception, disclosure expectations, or misuse. In context, this enables impersonation or misleading attribution in academic, professional, marketing, or social settings, increasing trust and provenance risks even though it is not direct code execution or data exfiltration.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description states the skill is specifically for Chinese AI-generated content, and the instructions throughout the file assume Chinese-only operation. This is a language/locale restriction expressed in natural language, but the skill does not provide any user opt-in, fallback, or explicit justification for why non-Chinese output is disallowed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file presents all skill-facing examples and headings exclusively in Chinese, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language context. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is reportable.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The title and positioning define the skill as a Chinese-only content polisher ('中文内容精修助手') with no indication that users may choose another language or that the locale restriction is a documented, justified requirement. The rule flags natural-language policy issues when a skill forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.