测试212
Security checks across malware telemetry and agentic risk
Overview
This is a planning workflow skill with broad but visible instructions and no evidence of hidden execution, credential access, exfiltration, or destructive behavior.
Install only if you want a structured brainstorming workflow that may activate broadly for creative tasks. Ask the agent to confirm before reading large parts of a repository, writing docs/plans files, or making git commits.
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.
