claude-intel-monitor
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a normal AI benchmark tool that uses your chosen model provider API key and saves local test history.
Before installing, understand that running tests may consume paid API quota, benchmark prompts are sent to the provider or custom base URL you configure, and watch mode will keep making periodic API calls until you stop it.
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
65/65 vendors flagged this skill as clean.