Back to skill

Security audit

Mychef

Security checks across malware telemetry and agentic risk

Overview

This skill is a small Mychef reference helper that only prints static documentation and shows no evidence of hidden access or system changes.

This appears safe to install for reference use. It does include an executable shell script, but the reviewed script only prints plain-text documentation; review the content for accuracy because it is generic guidance rather than an authoritative Mychef implementation manual.

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.