Snowflake Cortex AI Agent Security Governor

Use this skill to review the security and governance boundary of Snowflake AI: Cortex Agents and their identity and effective data reach, CORTEX_USER versus CORTEX_AGENT_USER and AI-function privileges including grants to PUBLIC, Cortex Search corpora as an untrusted-content surface, Cortex Analyst semantic exposure, tools and MCP connectors as privilege grants, prompt and indirect prompt injection, exfiltration paths, guardrails, adversarial evaluation, observability, and cost per successful task. Trigger before any Cortex or agentic capability is exposed to users. Static review only: it never creates or invokes an agent, and it never approves an AI system from its prompt.

VincentChuWaiChow Updated 24 repo stars

File contents

VincentChuWaiChow/vanguard-frontier-agentic commit d279fd454a

Frequently asked questions

npx get-skill add vincentchuwaichow/snowflake-cortex-ai-agent-security-governor