Nm Leyline Content Sanitization
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only defensive skill for sanitizing external content, with no included code or requested system access.
Safe to install as a written checklist. Do not assume it automatically sanitizes WebFetch, WebSearch, gh, or curl output unless you separately install and verify the upstream hook or plugin that provides that automation.
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.