Security audit
Ai Usage Policy
Security checks for vulnerabilities and agentic risk
Overview
This skill only guides an assistant to draft an AI usage policy and does not request hidden access, execution, persistence, or data export.
Before installing, users should be comfortable providing organizational policy context such as AI tools in use, data categories, and risk appetite. Treat the output as a practical draft for legal or compliance review, not legal advice.
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.