Security audit
Agent Isolation
Security checks for vulnerabilities and agentic risk
Overview
This is a prompt-only skill that helps users separate multi-agent workspaces and does not include hidden code or automatic actions.
Install this if you want written operating rules for separating multiple agents on the same machine. Before applying it, replace the example paths with your real workspaces and shared directories, and review any AGENT.md changes so they do not block legitimate collaboration workflows.
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
Static analysis
No suspicious patterns detected.