Back to skill

Security audit

classify-zero-shot

Security checks across malware telemetry and agentic risk

Overview

This skill is narrowly intended for text classification, but its required shell quoting pattern can be unsafe for crafted input text.

Review the shell quoting before installing. The skill should avoid fixed heredoc delimiters for arbitrary text or otherwise ensure user text cannot terminate the heredoc; also avoid sending sensitive/private text to the ZeroGPU classification service unless that data handling is acceptable.

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

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.