ClawHub
Back to skill

Security audit

Trump Style Copy Generator

Security checks across malware telemetry and agentic risk

Overview

This is a text-only style rewriting skill with broad activation wording, but it does not request code execution, data access, credentials, or background behavior.

Install only if you want a Trump-style rewriting helper available to the agent. Review outputs before public, professional, marketing, or political use, and avoid relying on this skill for neutral editing or fact-sensitive communications.

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
89% confidence
Finding
The description is broad enough to match generic rewriting, persuasion, and marketing requests, which can cause the skill to activate outside its intended niche. That increases the chance of inappropriate style transformation, brand-safety issues, or unwanted political persona emulation in unrelated user tasks.

Vague Triggers

Low
Confidence
81% confidence
Finding
The usage section provides broad positive triggers but no clear negative examples or boundaries, so an agent may invoke the skill for ordinary speechwriting, copyediting, or persuasion requests that do not actually ask for Trump-style output. In this context, the risk is mainly over-activation and misapplication rather than direct code or data compromise.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.