Agent Reliability
Security checks across malware telemetry and agentic risk
Overview
This skill is a small reliability helper library whose code matches its stated purpose and does not show hidden system access.
Safe to install for reliability metrics and consensus utilities. Be aware that it logs some supplied execution details to console by default, so avoid passing sensitive error messages or metadata unless that logging is acceptable, or disable logging in options.
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.