ClawHub
Back to skill

Security audit

paper-aigc-reducer

Security checks for vulnerabilities and agentic risk

Overview

This text-only skill is transparent about what it does, but its main purpose is to help academic or technical writing avoid AI-generation detection.

Install only if you are comfortable with a skill whose primary function is to rewrite or generate Chinese academic-style text to reduce AI-detection signals. It does not appear to access your files, credentials, network, or system settings, but its intended use may conflict with academic integrity or disclosure requirements.

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
  • 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 (5)

Natural-Language Policy Violations

Critical
Category
Not specified by scanner
Confidence
99% confidence
Finding

文件强制“所有输出和交互都使用中文”，未保留用户语言偏好或平台locale协商空间，属于策略层面的语言限制问题。其本身不是直接安全漏洞，但会降低系统可用性并可能导致用户误解安全或合规提示，在需要多语言澄清风险时更不利。

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

触发描述使用了“降AIGC、降重、论文改写、去除AI痕迹、让文本更像人写的、通过AI检测”等宽泛且相互重叠的自然语言条件，容易把普通润色、改写、学术写作帮助误路由到该技能。由于该技能本身又以规避检测为目标，误触发会把本来正常的用户请求带入违规能力链路，扩大被滥用范围。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

文件强制“所有输出和交互都使用中文”，未保留用户语言偏好或平台locale协商空间，属于策略层面的语言限制问题。其本身不是直接安全漏洞，但会降低系统可用性并可能导致用户误解安全或合规提示，在需要多语言澄清风险时更不利。

Content

No source excerpt is available for this finding.

Ssd 2

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

该技能把“规避AI检测”包装成“论文修改助手”“改写”“更像人写”的正常写作帮助，这是对真实能力目的的淡化。这样的表述会降低审核和使用者警觉性，使违规的检测规避能力更容易被集成、调用和规模化使用。

Content

No source excerpt is available for this finding.

Ssd 2

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

工作流在操作层面明确指导如何先生成内容、再系统性套用词汇替换、句式扩展和风格扰动，以实现“降AIGC”效果。这不是抽象描述，而是可执行的规避流程，会直接提升用户绕过检测器的成功率，尤其在学术文稿场景中危害更大。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.