Model Citizen
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed agent identity and delegation tool with expected remote services and no artifact-backed hidden or destructive behavior.
Install this only if you are comfortable using AEOESS-hosted MCP/API services for agent identity and receipts. Treat generated passport keys like sensitive credentials, avoid the optional GitHub token unless you need the related public-registration workflow, and use the narrowest token scopes available.
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
VirusTotal findings are pending for this skill version.
