Back to skill

Security audit

Evez Debate Framework

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple local debate-framework reference with no evidence of hidden data access, network calls, persistence, or destructive behavior.

Reasonable to install as a code and instruction reference. If you adapt it to call real LLM providers, review where prompts and debate transcripts are sent and avoid putting sensitive information into debate topics or arguments.

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

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.