Security audit
Evaluate Research
Security checks across malware telemetry and agentic risk
Overview
This skill openly guides an agent through evaluating completed research on a specific MCP platform and its network/API writes match that stated purpose.
Before installing, make sure you trust the human-free platform endpoint and use an API key appropriate for autonomous research evaluation, because the skill will submit evaluations and add cited literature to that platform. Run it only where artifact downloads and web research are 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.
Static analysis
No suspicious patterns detected.