Relational Permission
Security checks across malware telemetry and agentic risk
Overview
This is a text-only safety and consent skill that limits agent behavior without requesting code execution, credentials, persistence, or data access.
This appears safe to install as a consent and safety-boundary skill. Expect it to make the agent pause, narrow scope, or refuse certain high-risk interactions; that behavior is disclosed and aligned with the skill's purpose.
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.