SoK: Measuring What Matters for Closed-Loop Security Agents

• URL: http://arxiv.org/abs/2510.01654v1
• Date: Thu, 02 Oct 2025 04:20:35 GMT
• Title: SoK: Measuring What Matters for Closed-Loop Security Agents
• Abstract summary: We introduce CLASP: the Closed-Loop Autonomous Security Performance framework.<n>It aligns the security lifecycle (reconnaissance, exploitation, root cause synthesis analysis, patch synthesis, validation) with core agentic capabilities.<n>We then define the Closed-Loop Capability (CLC) Score, a composite metric quantifying both degree of loop closure and operational effectiveness.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cybersecurity is a relentless arms race, with AI driven offensive systems evolving faster than traditional defenses can adapt. Research and tooling remain fragmented across isolated defensive functions, creating blind spots that adversaries exploit. Autonomous agents capable of integrating, exploit confirmation, remediation, and validation into a single closed loop offer promise, but the field lacks three essentials: a framework defining the agentic capabilities of security systems across security life cycle, a principled method for evaluating closed loop agents, and a benchmark for measuring their performance in practice. We introduce CLASP: the Closed-Loop Autonomous Security Performance framework which aligns the security lifecycle (reconnaissance, exploitation, root cause analysis, patch synthesis, validation) with core agentic capabilities (planning, tool use, memory, reasoning, reflection & perception) providing a common vocabulary and rubric for assessing agentic capabilities in security tasks. By applying CLASP to 21 representative works, we map where systems demonstrate strengths, and where capability gaps persist. We then define the Closed-Loop Capability (CLC) Score, a composite metric quantifying both degree of loop closure and operational effectiveness, and outline the requirements for a closed loop benchmark. Together, CLASP and the CLC Score, provide the vocabulary, diagnostics, and measurements needed to advance both function level performance and measure closed loop security agents.

Related papers

• Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels [53.63220028820581]
  Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction.<n>We define trustworthy embodied intelligence as the sustained capacity to execute specified tasks reliably.
  arXiv  Detail & Related papers  (2026-07-28T17:50:44Z)
• Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response [0.0]
  Cyber-capable AI agents combine language models with tools, memory, and execution environments to perform offensive-security tasks.<n>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.
  arXiv  Detail & Related papers  (2026-07-28T07:34:37Z)
• SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents [87.26967184869198]
  SeClaw is a framework that combines specification-driven security task synthesis with execution-based security evaluation for Autonomous agents.<n> benchmark covers risks arising from resources, user tasks, environments, and intrinsic agent behaviors.
  arXiv  Detail & Related papers  (2026-06-01T14:23:42Z)
• Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security [57.35851886874902]
  Agentic AI systems execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that challenge trustworthiness.<n>This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployments.<n>For each dimension, we clarify key concepts, identify where risks emerge along the agent workflow, and summarize stage-targeted mitigation strategies.
  arXiv  Detail & Related papers  (2026-05-17T10:26:37Z)
• False Security Confidence in Benign LLM Code Generation [0.0]
  This note introduces a complementary but distinct framing: False Security Confidence (FSC)<n>FSC studies the same surface phenomenon from a measurement-first perspective in ordinary, non-attack-framed generation tasks.<n>We formalize FSC rate as the prevalence of security failure within the set of functionally correct outputs.
  arXiv  Detail & Related papers  (2026-04-18T14:52:26Z)
• SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization [50.71047638695205]
  Reasoning language models (RLMs) are increasingly used in programming.<n>Yet, even state-of-the-art RLMs frequently introduce critical security vulnerabilities in generated code.<n>We present SecPI, a fine-tuning pipeline that teaches RLMs to internalize structured security reasoning.
  arXiv  Detail & Related papers  (2026-04-04T04:29:11Z)
• Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats [29.43070870263607]
  We present a comprehensive security threat analysis of OpenClaw.<n>We examine threats across the agent's operational lifecycle, including indirect prompt injection, skill supply chain contamination, memory poisoning, and intent drift.<n>Our findings reveal critical weaknesses in current point-based defense mechanisms when addressing cross-temporal and multi-stage systemic risks.
  arXiv  Detail & Related papers  (2026-03-12T07:24:05Z)
• ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction [24.416258744287166]
  ICON is a probing-to-mitigation framework that neutralizes attacks while preserving task continuity.<n>ICON achieves a competitive 0.4% ASR, matching commercial grade detectors, while yielding a over 50% task utility gain.
  arXiv  Detail & Related papers  (2026-02-24T09:13:05Z)
• RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories [58.32028251925354]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, but their proficiency in producing secure code remains a critical, under-explored area.<n>We introduce RealSec-bench, a new benchmark for secure code generation meticulously constructed from real-world, high-risk Java repositories.
  arXiv  Detail & Related papers  (2026-01-30T08:29:01Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents [60.98294016925157]
  AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss.<n>We introduce Single-Shot Planning for CUAs, where a trusted planner generates a complete execution graph with conditional branches before any observation of potentially malicious content.<n>Although this architectural isolation successfully prevents instruction injections, we show that additional measures are needed to prevent Branch Steering attacks.
  arXiv  Detail & Related papers  (2026-01-14T23:06:35Z)
• Towards Verifiably Safe Tool Use for LLM Agents [53.55621104327779]
  Large language model (LLM)-based AI agents extend capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents.<n>LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records.<n>Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety.
  arXiv  Detail & Related papers  (2026-01-12T21:31:38Z)
• Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation [0.0]
  The current paper includes an example of agentic artificial intelligence (AI) based on autonomous software supply chain security.<n>It combines large language model (LLM)-based reasoning, reinforcement learning (RL), and multi-agent coordination.<n>Results show that agentic AI can facilitate the transition to self defending, proactive software supply chains.
  arXiv  Detail & Related papers  (2025-12-29T14:06:09Z)
• Cognitive Control Architecture (CCA): A Lifecycle Supervision Framework for Robustly Aligned AI Agents [1.014002853673217]
  LLM agents are vulnerable to Indirect Prompt Injection (IPI) attacks.<n>IPI attacks hijack agent behavior by polluting external information sources.<n>We propose the Cognitive Control Architecture (CCA), a holistic framework achieving full-lifecycle cognitive supervision.
  arXiv  Detail & Related papers  (2025-12-07T08:11:19Z)
• AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning [78.5751183537704]
  AdvEvo-MARL is a co-evolutionary multi-agent reinforcement learning framework that internalizes safety into task agents.<n>Rather than relying on external guards, AdvEvo-MARL jointly optimize attackers and defenders.
  arXiv  Detail & Related papers  (2025-10-02T02:06:30Z)
• STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents [38.755035623707656]
  This paper introduces Sequential Tool Attack Chaining (STAC), a novel multi-turn attack framework that exploits agent tool use.<n>We apply our framework to automatically generate and evaluate 483 STAC cases, featuring 1,352 sets of user-agent-environment interactions.<n>Our evaluations show that state-of-the-art LLM agents, including GPT-4.1, are highly vulnerable to STAC, with attack success rates (ASR) exceeding 90% in most cases.
  arXiv  Detail & Related papers  (2025-09-30T00:31:44Z)
• Secure and Scalable Face Retrieval via Cancelable Product Quantization [48.58859061524146]
  homomorphic encryption (HE) offers strong security guarantees by enabling arithmetic computations in the cipher space.<n>We propose Cancelable Product Quantization, a highly efficient framework for secure face representation retrieval.
  arXiv  Detail & Related papers  (2025-08-31T10:19:55Z)
• Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills [3.0620527758972496]
  This paper identifies and analyzes a novel vulnerability class in Model Context Protocol based agent systems.<n>The attack chain describes and demonstrates how benign, individually authorized tasks can be orchestrated to produce harmful emergent behaviors.
  arXiv  Detail & Related papers  (2025-08-27T01:11:59Z)
• ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning [49.47193675702453]
  Large Language Models (LLMs) have demonstrated remarkable generative capabilities.<n>LLMs remain vulnerable to malicious instructions that can bypass safety constraints.<n>We propose a reasoning-based safety alignment framework, ARMOR, that replaces the ad-hoc chains of thought reasoning process with human-aligned, structured one.
  arXiv  Detail & Related papers  (2025-07-14T09:05:54Z)
• SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems [10.393477652794747]
  Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use.<n>Despite their growing capabilities, today's agent frameworks remain fragile, lacking principled mechanisms for secure information flow, reliability, and multi-agent coordination.<n>We introduce SAFEFLOW, a new protocol-level framework for building trustworthy LLM/VLM-based agents.
  arXiv  Detail & Related papers  (2025-06-09T09:04:37Z)
• Criticality and Safety Margins for Reinforcement Learning [53.10194953873209]
  We seek to define a criticality framework with both a quantifiable ground truth and a clear significance to users.<n>We introduce true criticality as the expected drop in reward when an agent deviates from its policy for n consecutive random actions.<n>We also introduce the concept of proxy criticality, a low-overhead metric that has a statistically monotonic relationship to true criticality.
  arXiv  Detail & Related papers  (2024-09-26T21:00:45Z)
• Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions [60.26921219698514]
  We introduce a model-uncertainty-aware reformulation of CBF-based safety-critical controllers. We then present the pointwise feasibility conditions of the resulting safety controller. We use these conditions to devise an event-triggered online data collection strategy.
  arXiv  Detail & Related papers  (2022-08-23T05:02:09Z)
• Safe RAN control: A Symbolic Reinforcement Learning Approach [62.997667081978825]
  We present a Symbolic Reinforcement Learning (SRL) based architecture for safety control of Radio Access Network (RAN) applications. We provide a purely automated procedure in which a user can specify high-level logical safety specifications for a given cellular network topology. We introduce a user interface (UI) developed to help a user set intent specifications to the system, and inspect the difference in agent proposed actions.
  arXiv  Detail & Related papers  (2021-06-03T16:45:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.