Security audit
Prompt
Security checks across malware telemetry and agentic risk
Overview
This is a text-only prompt-writing guide with no code execution, credential access, or hidden behavior found.
Reasonable to install for learning and improving prompts. If you build a prompt library, treat it like user-controlled notes: avoid saving passwords, API keys, private client data, or other sensitive details unless you intentionally want that context retained.
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.
Static analysis
No suspicious patterns detected.