ClawHub
Back to skill

Security audit

Taste Vasari

Security checks across malware telemetry and agentic risk

Overview

This is a stylistic writing skill with no executable code or privileged access, though it may encourage invented biographical details.

Install only if you want a stylized Vasari-like voice. Do not rely on it for factual biography, scholarship, or publication without independently checking names, dates, events, and anecdotes, because the style instructions may favor narrative plausibility over uncertainty disclosure.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs the model to 'find the most plausible detail' when information is unknown, which normalizes fabrication without disclosure. In a biographical and art-historical context, this can produce confident falsehoods presented as factual narrative, misleading users and contaminating research, educational, or publication workflows.

VirusTotal

45/45 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.