Multi-Model Response Comparator
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward guide for comparing multiple AI model responses, with no hidden installer, executable code, persistence, or destructive behavior found.
Before installing, understand that using the included provider example would send prompts and model outputs to an external OpenAI-compatible service such as Crazyrouter. Use appropriate API keys, avoid sending sensitive prompts unless your provider terms allow it, and treat inferred cost or latency notes as estimates unless you supply measured data.
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.