Skylv Agent Constitution Guard
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only safety skill for defining agent permission guardrails, with no executable installer or hidden behavior found.
Install only if you want guidance for designing agent permission boundaries. Treat its examples as templates, review any rules you create carefully, and remember that this skill is documentation rather than an enforcement engine by itself.
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
63/63 vendors flagged this skill as clean.