Now in early access, book a 30-minute demo →
Agent Skill security

Kimi Code CLI

Moonshot AI's open-source terminal coding agent with subagent support.

Moonshot AI

How skills run on Kimi Code CLI

Kimi Code CLI edits code, runs shell commands, fetches web pages, and dispatches subagents in isolated contexts. Those parallel runs draw on the same local skill directories, so one hostile skill can act repeatedly without a human reading each step.

Skill security, assessed

Every public skill in our index is assessed by the Anomity Skill Intelligence engine against its real source: remote code execution, credential and data exfiltration, prompt injection, and unsafe installers.

Browse the Skill Risk Index →

Govern the skill layer on Kimi Code CLI

Scanning a skill before use tells you what it claims to do. Anomity's Endpoint Sensor sees what agents actually do at runtime: it discovers every skill, agent, and MCP server on the endpoint, and policy can allow, deny, or log the tool calls a skill triggers on Kimi Code CLI and every other agent. Violations route to your SIEM, Slack, email, or Jira with a queryable 90-day audit trail.

Book a 30-minute demo to see your own agent and skill inventory.

Other agents

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok