Security audit
Kimi Desktop Gateway Policy
Security checks for vulnerabilities and agentic risk
Overview
This skill is a narrowly scoped guidance document that tells agents not to manipulate Kimi/OpenClaw gateway processes directly and to ask the user to restart the desktop app instead.
Install this if you want agents to handle Kimi/OpenClaw gateway problems by advising a full Kimi Desktop restart instead of running terminal repair commands. Be aware it may intentionally steer agents away from CLI-based gateway fixes in those situations.
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.