Back to skill

Security audit

extract-entities

Security checks across malware telemetry and agentic risk

Overview

The skill’s purpose is coherent, but its required shell command formatting can let specially crafted input escape the text wrapper and run unintended shell commands.

Review this skill before installing. It should use a safer way to pass text to `zerogpu extract_entities`, such as a collision-resistant delimiter, stdin/file input, or structured argument escaping. Avoid using it on untrusted arbitrary text until that command-formatting issue is fixed.

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.