Coinranking
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are coherent development and maintenance helpers with disclosed commands and no evidence of hidden install, persistence, exfiltration, or deceptive behavior.
Before installing, understand that these are maintainer/developer skills: moderation commands can change user or skill state, GitHub workflows can comment or publish proof artifacts, and autoreview can run a full-access nested review. Use them in trusted repos with appropriate credentials and review confirmation prompts before write actions.
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.