Security audit
Chesterton's Fence
Security checks across malware telemetry and agentic risk
Overview
This is a reasoning and coaching skill that helps users investigate why an existing rule, process, or code path exists before removing it.
This skill is appropriate if you want an agent to slow down removals of existing rules, processes, or code until their purpose is understood. Expect it to ask for context and sometimes recommend checking history before making changes.
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.
Static analysis
No suspicious patterns detected.