ClawHub
Back to skill

Security audit

paper-writing-studio

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed academic writing workflow skill with broad triggers but no hidden access, persistence, credential use, or destructive behavior.

Install this if you want structured Chinese-language support for journalism and communication thesis writing. Review generated citations and literature claims carefully, and avoid pasting sensitive unpublished research into any third-party tools the skill suggests unless you are comfortable sharing it there.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill is marked user-invocable and described in very broad terms such as helping with 'write a paper' or related generic academic tasks. These broad triggers can cause the skill to activate for common requests outside the user's intent, leading to inappropriate routing, over-collection of context, or workflow hijacking of general writing conversations.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The activation phrases listed in the applicability section are expansive and overlap with ordinary user requests like 'help me write a paper' or 'write a literature review.' In a user-invocable skill, this increases the chance of accidental invocation and can steer benign, ambiguous requests into a specialized workflow the user did not request, reducing user control and potentially exposing additional files/scripts unnecessarily.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.