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

ZCode

Z.ai's agentic development environment, a desktop app built around GLM models.

Z.ai

How skills run on ZCode

ZCode gives its agent a file manager, terminal, Git panel, and browser preview, and can run several agents in parallel over one project. Skills that arrive from a registry are unreviewed instructions with access to all of it.

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 ZCode

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 ZCode 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