Security audit
Prompt Engineering Lab
Security checks across malware telemetry and agentic risk
Overview
This skill is a prompt-writing guidance document and does not include executable code, credential handling, persistence, or hidden behavior.
This appears safe to install if you want prompt engineering templates and workflows. As with any prompt-design helper, review generated prompts before using them in regulated or production settings, especially for medical, legal, financial, or customer-facing systems.
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.