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.
Abstract
Agentic security uses large-language-model (LLM) agents to plan, dispatch, and interpret security tools. As these systems move from demonstrations to deployed products, practitioners repeatedly encounter the same operational failures. We systematize these failures through a hands-on evaluation of ten widely used static, dynamic, cloud, orchestration, and AI red-teaming tools for unattended pipelines. We introduce a four-dimensional Integration Friction Index that separates one-time engineering cost from recurring organisational, legal, and maintenance cost. We then derive quantitative regularities that explain recurring failure modes. Modelling an agentic security system as stochastic LLM policies wrapped by a deterministic mediator, we show that long-lived sessions lose resident evidence with phase count, while short-lived sub-agents extend the usable horizon according to the compression ratio between raw evidence and its summary. We show that a two-stage verdict cascade multiplies scorer likelihood ratios, but provides little benefit when scorer errors correlate. We show that treating unevaluable outcomes as attack failures biases downstream measurements toward evasive and severe responses. We formulate planner-versus-worker model routing as a knapsack problem and derive a closed-form execution cap for heavy-tailed tools, eta* = alpha v/c. Finally, we show why scope and budget enforcement cannot be delegated to system prompts: prompts do not constrain what actually executes. Inspectra, our implemented platform, serves as a worked instantiation, with mechanisms labelled shipped, partial, or planned, including those that did not work.
Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating failures that local checks may miss. Without an execution-level view, a multi-agent setting can easily be mistaken for evidence of a genuinely multi-agent security effect. We thus systematize MAS security through an execution-centered analysis of 197 works, covering six interaction interfaces, four adversary positions, seven system-level risks, and eight recurring attack paths. We introduce an A-I-R framework that organizes attacks by adversary position, interaction interface, and resulting system-level risk, unifying otherwise fragmented attack mechanisms across MAS. We organize defenses through a five-part contract covering path target, observation, intervention, trust boundary, and recovery, and identify path closure and recovery as key challenges. We audit 44 evaluation and benchmark works and identify open challenges in isolating interaction effects, designing comparable and diagnostic metrics, supporting reuse across MAS designs, and evaluating open-system operation. Together, these findings motivate an interaction-aware view of MAS security: trace attacks end to end, test whether defenses close those paths, and evaluate system-level effects with appropriate counterfactuals.
Rui Yang, Jun-Jie Xu, Zhengyu Liu 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
RedAgentBench is introduced, an executable framework for autonomous red-teaming and faithful measurement that shows that executable evaluation can improve safety measurement and identify actionable intervention points.
Zixing Chen, Xingyuan Liu, Jie Zhu et al.· 1 citation
Cyber-capable AI agents combine language models with tools, memory, and execution environments to perform multi-step offensive-security tasks. Existing work separately measures cyber capability and catalogs attacks against agent components, but provides less guidance on containing a capable agent within the environments used to evaluate it. This review synthesizes five vulnerability classes at that boundary: multi-step offensive chains, objectives that conflict with sandbox boundaries, supply-chain and credential exposure, persistent command-and-control, and the speed of automated action. We use two separate preliminary incident records: the reported July 2026 Hugging Face/OpenAI evaluation breach and Anthropic's subsequent three-incident evaluation review. A comparative evidence protocol distinguishes record-specific factual claims from the shared systems lesson: the evaluation environment is itself part of the security boundary. Across the taxonomy and records, we examine controls for containment, privilege separation, provenance, and responder access, including the dual-use problem that defensive artifacts may also enable misuse. The review identifies practical priorities for evaluating cyber capability together with the security of the environment in which that capability is exercised.
It is shown that the more consequential risks lie one layer down, in the protocol between agents and commerce services, and a platform-agnostic defense that drives the structural attack-success rate to zero for four of the five structural classes.
This paper introduces a compositional model explaining why no component is catastrophic alone, yet their conjunction can produce correlated destructive action, and separates three population-reach routes from a common core of dormancy, activation, authority, reachable targets, and failed recovery.
Satoshi Matsuoka· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
