Security audit
Ai Fencing
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward fencing coaching reference with no hidden commands, persistence, credential handling, or broad system access.
Reasonable to install if you want fencing guidance. Treat technique, training, equipment, and rule advice as general coaching support rather than a substitute for a qualified instructor, current federation rules, or safety supervision.
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.