Cursor
The AI-native code editor. Rules and skills extend every Cursor agent run.
AnysphereHow skills run on Cursor
Cursor's agent reads project rules and skills to shape its behavior. Untrusted skill content pulled into that context can redirect the agent, exfiltrate files it can read, or run commands through the integrated terminal.
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 Cursor
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 Cursor 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.
