World Building
Security checks across malware telemetry and agentic risk
Overview
This is a writing-focused worldbuilding skill that gives structured instructions for creating and updating a story lorebook, with no evidence of hidden code, data access, or unsafe behavior.
This skill appears safe to install for story planning. Expect it to produce long markdown lorebooks and ask for story premise or outline details; review generated lore for quality and consistency, but there is no artifact-backed sign of credential use, hidden persistence, or external data handling.
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
64/64 vendors flagged this skill as clean.