How skills run on Zed
Zed's agent runs tools and edits with your permissions. Skills and rules that guide it are untrusted input, and a malicious one can shape which actions it takes on your machine.
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.
Govern the skill layer on Zed
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 Zed 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.
