ClawHub
Back to skill

Security audit

Paper Writing Workflow

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent academic paper-writing workflow with only a small local helper script and no evidence of credential access, network access, destructive actions, or hidden persistence.

This appears safe to install for academic drafting, but treat it as a workflow coordinator: review any companion skills it calls, expect local Markdown output when using the helper script, and verify generated citations, claims, and journal formatting before relying on the result.

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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger keywords are broad and overlap with ordinary academic-writing requests such as 'paper writing' and 'thesis writing'. This can cause the workflow to activate unintentionally for generic requests, expanding the skill's scope and potentially invoking multiple downstream writing/research skills without the user explicitly requesting this workflow.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal