ClawHub
Back to skill

Security audit

bozo-writer

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only writing helper for Chinese AI short-video scripts and does not request files, credentials, tools, or code execution.

Install this if you want a specialized Chinese short-video script formatter for AI education topics. Be aware it may push matching requests into a fixed Chinese oral-script structure, so review outputs for language, platform fit, accuracy, and originality before publishing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 description is broad enough to activate on common writing or rewriting requests that may only tangentially relate to this niche skill. In a multi-skill environment, this can cause inappropriate routing, override user intent, and lead the agent to apply specialized instructions in contexts where they were not requested.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The skill hard-codes a Chinese internet and beginner-tech audience context without checking whether the user asked for that locale, audience, or language. This can mis-handle user requests, produce unwanted linguistic transformation, and create instruction precedence issues where the skill's defaults override explicit or implicit user preferences.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The output section mandates Chinese short-video phrasing and oral-script structure with no opt-in or fallback path. If auto-invoked, the skill may force content into a specific language and platform style, causing unauthorized transformation of user content and reducing reliability of the broader assistant behavior.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.