Security audit
Kimi Desktop Gateway Policy
Security checks across malware telemetry and agentic risk
Overview
This skill is a narrow troubleshooting policy that tells agents not to manipulate Kimi/OpenClaw gateway processes directly and instead asks the user to restart the desktop app.
Installers should understand that this skill will make the agent avoid direct gateway process fixes and instead tell users to fully quit and reopen Kimi Desktop when gateway lifecycle problems occur.
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
VirusTotal engine telemetry is currently stale for this artifact.
Static analysis
No suspicious patterns detected.