Security audit
Ethical Thinking
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only ethics review framework that does not add code execution, data access, persistence, or hidden behavior.
This skill is appropriate to install if you want the agent to use a structured ethics-review format. It will shape how ethical tradeoffs are framed, but it does not grant new tools, read private data, run code, or persist anything.
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
VirusTotal findings are pending for this skill version.
Static analysis
No suspicious patterns detected.