Key‑Safe Skill Generator
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill about safer credential-handling patterns, with no executable files or hidden runtime behavior found.
Installers should understand that this skill teaches workflows involving credential storage and local MGC tooling. The skill itself does not run code, but any generated skills based on it should be reviewed carefully to ensure they do not print secrets, overbroadly read credential stores, or perform sensitive actions without explicit user approval.
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
62/62 vendors flagged this skill as clean.