Task Analyzer
Security checks across malware telemetry and agentic risk
Overview
This skill only instructs an agent to analyze tasks and return structured recommendations, with no code execution, persistence, credential use, or hidden data movement evident.
This appears safe to install for task-analysis workflows. It will steer the agent toward structured Chinese-language analysis and recommendations rather than direct execution, so use it when you want planning and risk review, not when you want the task performed immediately.
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.