Cortex AI Guardrails¶

Overview¶

Cortex AI Guardrails, part of the Snowflake Horizon Catalog, provide run-time protection against prompt injection and jailbreak attacks on Cortex Code, Snowflake Intelligence, and Cortex Agents.

As enterprises move AI applications from pilot to production, they face increased risk from adversarial prompts that can threaten data integrity and security. Cortex AI Guardrails extend Snowflake’s default protections against known prompt injection techniques by adding guardrails to detect and mitigate adversarial threats.

Integrated centrally into Snowflake Horizon Catalog, Cortex AI Guardrails leverage contextual reasoning to detect and neutralize malicious intent, preventing adversarial threats from circumventing established security boundaries and hardened permissions.

Key capabilities¶

Cortex AI Guardrails provide the following protections:

• Prompt injection detection: Identifies and blocks attempts to override system instructions through malicious prompts, including indirect prompt injections embedded in tool calls.
• Jailbreak prevention: Detects attempts to bypass the model’s safety protocols and security boundaries.
• Zero-day style protection: Uses advanced techniques to identify sophisticated, previously unknown attack patterns in real time.

Configure Cortex AI Guardrails¶

You can configure Cortex AI Guardrails at the account level using the AI_SETTINGS parameter. This provides centralized control over guardrail behavior for Cortex Code, Snowflake Intelligence, and Cortex Agents in your account. Users with the ACCOUNTADMIN role can configure Cortex AI Guardrails.

Enable guardrails¶

To enable Cortex AI Guardrails for your account, use the ALTER ACCOUNT command with the AI_SETTINGS parameter:

ALTER ACCOUNT SET AI_SETTINGS = $$
  guardrails:
    advanced_prompt_injection:
      - enabled: true
$$;

View guardrail settings¶

To view the current guardrail configuration for your account:

SHOW PARAMETERS LIKE 'AI_SETTINGS' IN ACCOUNT;

Disable guardrails¶

To disable Cortex AI Guardrails:

ALTER ACCOUNT UNSET AI_SETTINGS;

Monitor guardrail activity¶

When Cortex AI Guardrails detect a potential threat, the event is logged for audit and monitoring purposes.

• Cortex Code: Review detected threats in the conversation logs. For where those logs are stored and how to manage them, see Conversation history.
• Snowflake Intelligence and Cortex Agents: Review conversation and trace data in Cortex Agent monitoring (for example in Snowsight, AI & ML » Agents, then the Monitoring pane for the agent). For details, see Monitor Cortex Agent requests.

With that information (conversation logs on Cortex Code, or monitoring and trace data for agents), you can:

• Monitor for attempted attacks against your AI workloads
• Identify patterns in blocked or flagged requests
• Audit guardrail effectiveness

Considerations¶

• While Cortex AI Guardrails are optimized for high accuracy, some legitimate prompts may occasionally be flagged. Review your guardrail logs periodically to identify any patterns.
• Cortex AI Guardrails for prompt injection are currently available with Cortex Code, Snowflake Intelligence, and Cortex Agents.

Cost¶

You are charged credits for the use of Cortex AI Guardrails as listed in the Snowflake Service Consumption Table. Usage is measured based on the number of tokens scanned.

Related topics¶

• Snowflake Horizon Catalog
• Cortex Code
• Overview of Snowflake Intelligence
• Cortex Agents
• Snowflake AI and ML