Jailbreak Detection Check
dcl_evaluate_jailbreakDetect jailbreak attempts in LLM responses before action. Evaluates output against instructions to identify security breaches and ensure policy compliance.
Instructions
PRE-ACTION Instruction Adherence Check ($0.02). Detects jailbreak attempts.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | Identifier of the agent that produced the response. | |
| response | Yes | The agent or LLM response text to check for jailbreak attempts. | |
| payment_id | No | Optional payment identifier returned by a previous call when payment is required |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| reason | Yes | Human-readable explanation of why the verdict was reached. | |
| tx_hash | Yes | Hash of this record in the tamper-evident audit chain. | |
| verdict | Yes | COMMIT if the response passed policy checks, otherwise NO_COMMIT. | |
| seal_text | Yes | Human-readable Leibniz Layer verification seal. | |
| timestamp | Yes | Unix timestamp when this record was sealed. | |
| confidence | Yes | Confidence score of the verdict, from 0.0 to 1.0. | |
| drift_mode | Yes | Current drift status: NORMAL, WARNING, ESCALATION, or BLOCK. | |
| input_hash | Yes | Hash of the evaluated response (raw content is never stored). | |
| verify_url | Yes | Public URL to independently verify this seal. | |
| chain_index | Yes | Sequential index of this record in the audit chain. | |
| drift_score | Yes | Z-score measuring deviation of the recent commit rate from baseline. | |
| policy_version | Yes | Version of the policy that was applied. |