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

Cortex Code

Snowflake's data agent for SQL, Python, and dbt work, in Snowsight and a CLI.

Snowflake

How skills run on Cortex Code

Cortex Code executes SQL and DDL against a Snowflake account, reads and writes files, and manages git repositories. Skills loaded from the user's home directory apply to an agent holding live warehouse credentials, which raises the stakes on every skill it trusts.

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 Cortex Code

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 Cortex Code 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