Security audit
Chesterton's Fence
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only reasoning skill that asks agents to investigate before removing rules, code, or processes, with no hidden execution or data access.
Before installing, expect this skill to make agents pause and ask for history before deleting or repealing something. That behavior is the point of the skill. It does not appear to add code execution, credential use, background workers, or broad local indexing.
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.