Skip to content
Human Intelligence seal
Human Intelligence
§ I · Domain INP · Control 5 of 10
Control
INP-05
Edition
v.1.3
Status
Public review

INP · Input & Prompt Security

INP-05Jailbreak pattern library

A jailbreak pattern library is maintained and continuously updated. Inputs are evaluated against known patterns prior to processing.

The organization maintains a continuously updated library of known jailbreak patterns, escape sequences, and adversarial prompt templates. All inputs are evaluated against this library before reaching the model. The library is updated as new attack patterns are discovered through red-team assessments, community disclosures, and production monitoring.

Table INP-05.1 · Maturity criteria · v.1.3

L1 to L5 · the lowest level in scope caps the agent
L1Ad hoc

Controls exist informally; documentation is incomplete; no consistent review.

L2Documented

Controls are written down; ownership is assigned; review cadence is defined.

L3Operated

Controls are followed in practice; evidence is collected; deviations are tracked.

Pattern library exists and is current; inputs are evaluated against it in real time; the library has been updated within the prior quarter; new patterns from red-team and production findings are incorporated.

L4Measured

Control effectiveness is measured against documented thresholds; trends are reported.

L5Continuously Improved

Controls evolve based on incident learning; maturity gains are evidenced over time.

The v1.3 edition publishes a control-specific criterion at L3 (Operated). The other levels apply the general ladder to this control; see the maturity ladder.

Evidence an assessor asks for

  1. E.1

    Pattern library exists and is current.

  2. E.2

    Inputs are evaluated against it in real time.

  3. E.3

    The library has been updated within the prior quarter.

  4. E.4

    New patterns from red-team and production findings are incorporated.

Table INP-05.2 · Framework mappings

6 of 7 frameworks carry a control-level reference
NIST AI RMFMEASURE 2.7NIST AI Risk Management Framework 1.0
ISO/IEC 42001·ISO/IEC 42001:2023 · Artificial intelligence management system
OWASP LLM Top 10LLM01OWASP Top 10 for Large Language Model Applications
SOC 2 (TSC)CC7.1AICPA Trust Services Criteria for SOC 2 Type II
EU AI ActArt. 15(4)EU AI Act · Regulation (EU) 2024/1689
MITRE ATLASInitial AccessMITRE ATLAS · Adversarial Threat Landscape for AI Systems
SingaporeMAIGF Security, AI Verify SecuritySingapore Model AI Governance Framework / AI Verify / PDPA

Mappings are directional: meeting this control evidences but does not by itself satisfy the external requirement. A middle dot means no control-level reference is published at this edition; see the crosswalk.

Cite this control

Human Intelligence. HI-AAF v1.3, INP-05 Jailbreak pattern library. Public review edition, July 2026. https://humanintel.net/standard/inp/inp-05

Edition v.1.3 · July 2026 · Public review · Markdown · PDF

https://humanintel.net/standard/inp/inp-05

Notice

HI-AAF v1.3 is an independent framework published by Human Intelligence. It is not affiliated with NIST, ISO, AICPA, or any government or accreditation body. The framework is offered openly for review during the current draft cycle.