Kimi Code API
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only guide for configuring Kimi as an external coding model, with expected API-key and third-party data-sharing considerations.
Install or use this only if you intend to send OpenClaw or Claude Code prompts and coding context to Kimi. Keep real API keys out of committed config, pasted source, screenshots, and logs, and confirm third-party model use is allowed for your project.
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
66/66 vendors flagged this skill as clean.