This work proposes the Policy-Evidence-Execution Separation Pattern, implemented by the Trustworthy AI Posture (TAIP) Assurance Engine and operated as Continuous Control Posture Assurance (CCPA) and is evaluated across increasing numbers of independent Decision Gateway contexts.
Abstract
Large language model (LLM)-based repository auditors are increasingly deployed as security controls within continuous integration (CI) pipelines, where their findings admit, block, or delay software changes. As Agentic Software Development Life Cycle (SDLC) Security Controls, their non-deterministic behaviour changes the evidence, while organisational risk appetite and jurisdictional or data-sovereignty policy change its interpretation. Point-in-time audits therefore cannot maintain current assurance for merge decisions. We propose the Policy-Evidence-Execution Separation Pattern, implemented by the Trustworthy AI Posture (TAIP) Assurance Engine and operated as Continuous Control Posture Assurance (CCPA). By separating policy from stable execution and binding admitted evidence to a versioned Posture Tree, the same assurance logic operates across models, environments, and policy profiles. We evaluate the approach using unmodified RepoAudit on a fixed Python Null Pointer Dereference benchmark. The retained evidence repository contains 80 RepoAudit executions across two OpenAI model configurations, gpt-4o-mini and gpt-4.1. TAIP recomputes assurance posture after policy, evidence, and model-context changes and is evaluated across increasing numbers of independent Decision Gateway contexts. The maximum observed policy-to-posture latency was 1.1 ms across three policy-class cycles in one execution. At 1,000 independent assurance contexts, full policy-triggered recomputation with one worker recorded a maximum aggregate refresh of 1.62 s, below the predeclared 5 s Decision Gateway budget. These single-host measurements concern assurance over retained evidence and exclude RepoAudit execution and provider inference.
Security Operations Centers (SOCs) face increasing pressure from alert fatigue and complex incident response requirements across heterogeneous production environments. While Large Language Models (LLMs) show promise in automating security workflows, their deployment in production settings raises significant concerns ab...
Wen-Rui Ma, Wan-Rong Cai, Tian-Yu Yu et al.· 2026 6th International Confe...· 0 citations
A four-dimensional Integration Friction Index is introduced that separates one-time engineering cost from recurring organisational, legal, and maintenance cost and shows why scope and budget enforcement cannot be delegated to system prompts.
Israt Moyeen Noumi, Tarannum Ahmed Nowshin, Md Mehedi Hasan Nipu et al.· 0 citations
This work argues that agentic risk is progressive: it can enter at four loci of the agent control loop--skill admission, invocation-time intent, execution-time effect, and post-action consequence--while a denied dangerous objective can reappear across surface forms, tools, or turns.
Kai Wang, Zeming Wei, Biaojie Zeng et al.· 0 citations
Multi-agent LLM pipelines increasingly span organisational boundaries; when a fault surfaces, someone must determine where it entered. The artifact available is rarely a full execution trace: it is the reports each agent filed, and a filed report can state a conclusion alongside its observations. Using a pre-registered...
The Zero-Trust Automation Lifecycle (ZTAL) is proposed, a methodology that threads continuous Zero-Trust verification throughout the twelve-stage low-code development process and offers practitioners an artifact-driven blueprint for securing composable AI systems and a working reference implementation on which the full...
Owuala Senator Obinwanne, Ike Bright Ikemdinachi, Omoyeni Oluwakemi et al.· International Journal of Art...· 0 citations
Banks increasingly place machine learning at the point of decision, and those systems change continuously through retraining, threshold tuning and challenger promotion. Control assurance has not kept pace. Controls are still validated discretely, at a quarterly review, an annual validation or a single audit sample, so...
Yashaswini Nalla· International journal of com...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.