d
Security checks across malware telemetry and agentic risk
Overview
This skill is a harmless ASCII-art guide, though its listing summary appears stale or mismatched.
Safe to install from a security perspective if you want an ASCII-art helper. Do not rely on the current listing summary for Docker, OpenClaw agent deployment, or multi-agent setup unless the publisher corrects the metadata to match the actual skill.
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
66/66 vendors flagged this skill as clean.