ClawHub

Writing Style Cloner - 个人写作风格克隆器

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only writing helper that rewrites drafts into a disclosed Chinese personal writing style and does not request code execution, credentials, network access, or persistence.

Install this if you specifically want Chinese drafts rewritten in Antonia's self-media style. For general writing help, academic/legal/business writing, another language, or neutral tone, explicitly tell the agent not to use this style or choose a narrower writing skill.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases are broad, common requests such as '帮我写文章' and '写成文章', which can match many normal conversations and cause the skill to activate when the user did not specifically intend to invoke this style-cloning behavior. In practice, that can override user expectations, apply unintended rewriting rules, and increase the chance that the assistant transforms content into a fixed persona/style without clear consent.

Natural-Language Policy Violations

Medium
Confidence
83% confidence
Finding
The skill description and overall behavior are hard-wired to Chinese output and a specific persona's style without indicating user choice, opt-in, or locale justification. That creates a policy/control issue where the assistant may steer output into a language or format the user did not request, reducing user agency and potentially causing incorrect or unusable responses for multilingual contexts.

Natural-Language Policy Violations

Medium
Confidence
86% confidence
Finding
The skill prescribes a fixed Chinese writing structure, terminology, and output style as mandatory behavior rather than as an optional transformation selected by the user. This can lead to unintended content manipulation, especially when the source material requires neutrality, another language, or a different register, and the rigid format increases the risk of misaligned outputs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal