Clawed and Dangerous: Can We Trust Open Agentic Systems?

• URL: http://arxiv.org/abs/2603.26221v1
• Date: Fri, 27 Mar 2026 09:45:12 GMT
• Title: Clawed and Dangerous: Can We Trust Open Agentic Systems?
• Abstract summary: Open agentic systems combine planning with external capabilities, persistent memory, and privileged execution.<n>This paper introduces a six-dimensional analytical taxonomy and synthesizes 50 papers spanning attacks, benchmarks, defenses, audits, and adjacent engineering foundations.<n>Our review shows that the literature is relatively mature in attack characterization and benchmark construction, but remains weak in deployment controls, operational governance, persistent-memory integrity, and capability revocation.
• Score: 12.04979073308511
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this broader class. Without much attention yet, their security challenge is fundamentally different from that of traditional software that relies on predictable execution and well-defined control flow. In open agentic systems, everything is ''probabilistic'': plans are generated at runtime, key decisions may be shaped by untrusted natural-language inputs and tool outputs, execution unfolds in uncertain environments, and actions are taken under authority delegated by human users. The central challenge is therefore not merely robustness against individual attacks, but the governance of agentic behavior under persistent uncertainty. This paper systematizes the area through a software engineering lens. We introduce a six-dimensional analytical taxonomy and synthesize 50 papers spanning attacks, benchmarks, defenses, audits, and adjacent engineering foundations. From this synthesis, we derive a reference doctrine for secure-by-construction agent platforms, together with an evaluation scorecard for assessing platform security posture. Our review shows that the literature is relatively mature in attack characterization and benchmark construction, but remains weak in deployment controls, operational governance, persistent-memory integrity, and capability revocation. These gaps define a concrete engineering agenda for building agent ecosystems that are governable, auditable, and resilient under compromise.

Related papers

• HazardAuditor: From Executable Threats to Safer Computer-Use Agents [50.06351661912873]
  Existing guard models target static prompts and responses.<n>Existing safety platforms produce evaluation verdicts rather than the normalized supervision a guard model needs to learn.<n>We introduce HazardAuditor, an execution-grounded framework that closes both gaps.
  arXiv  Detail & Related papers  (2026-09-14T07:09:33Z)
• Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges [0.0]
  This survey delivers a comprehensive systems-security reference framework for trustworthy agentic AI.<n>We formalize the general agent architecture as a stateful 5-tuple and establish a 6-dimensional trustworthiness taxonomy covering security, safety, privacy, explainability, fairness, and accountability.
  arXiv  Detail & Related papers  (2026-09-12T05:51:27Z)
• 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)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Position: AI Safety Requires Effective Controllability [7.789894640525689]
  We argue that AI safety requires controllability as a first-class objective.<n>Experiments with OpenClaw-based agents show that current alignment and guardrail mechanisms reduce risk, but often fail to provide persistent, authoritative, and enforceable runtime control.
  arXiv  Detail & Related papers  (2026-05-26T14:53:24Z)
• AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents [16.761926457126428]
  This paper presents AgentWard, a lifecycle-oriented, defense-in-depth architecture that systematically organizes protection across five stages.<n>AgentWard integrates stage-specific, heterogeneous controls with cross-layer coordination, enabling threats to be intercepted along their propagation paths while safeguarding critical assets.
  arXiv  Detail & Related papers  (2026-04-27T16:22:27Z)
• Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw [42.9467373594646]
  This report presents a comprehensive security analysis of the OpenClaw ecosystem.<n>We highlight critical vulnerabilities such as prompt injection-driven Remote Code Execution (RCE), sequential tool attack chains, context amnesia, and supply chain contamination.<n>To address these systemic architectural flaws, we introduce the Full-Lifecycle Agent Security Architecture (FASA)<n>This theoretical defense blueprint advocates for zero-trust agentic execution, dynamic intent verification, and cross-layer reasoning-action correlation.
  arXiv  Detail & Related papers  (2026-03-13T04:33:05Z)
• Extending the Formalism and Theoretical Foundations of Cryptography to AI [18.724847875398435]
  Recent progress in (Large) Language Models has enabled the development of autonomous LM-based agents.<n>One emerging direction to mitigate security risks is to constrain agent behaviours via access control and permissioning mechanisms.<n>We first systematize the landscape by constructing an attack taxonomy tailored to language models.<n>We then develop a formal treatment of agentic access control by defining an AIOracle algorithmically and introducing a security-game framework.
  arXiv  Detail & Related papers  (2026-03-03T04:11:21Z)
• The Alignment Flywheel: A Governance-Centric Hybrid MAS for Architecture-Agnostic Safety [5.399984738447277]
  This paper formalizes the Alignment Flywheel as a governance-centric hybrid MAS architecture.<n>An enforcement layer applies explicit risk policy at runtime, and a governance MAS supervises the Oracle through auditing, uncertainty-driven verification, and versioned refinement.<n>The architecture is implementation-agnostic with respect to both the Proposer and the Safety Oracle, and specifies the roles, artifacts, protocols, and release semantics needed for runtime gating, audit intake, signed patching, and staged rollout.
  arXiv  Detail & Related papers  (2026-02-28T00:48:06Z)
• LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios [51.52395368061729]
  We present LPS-Bench, a benchmark that evaluates the planning-time safety awareness of MCP-based CUAs under long-horizon tasks.<n> Experiments reveal substantial deficiencies in existing CUAs' ability to maintain safe behavior.<n>We propose mitigation strategies to improve long-horizon planning safety in MCP-based CUA systems.
  arXiv  Detail & Related papers  (2026-02-03T08:40:24Z)
• Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [65.6660735371212]
  We present textbftextscJustAsk, a framework that autonomously discovers effective extraction strategies through interaction alone.<n>It formulates extraction as an online exploration problem, using Upper Confidence Bound--based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration.<n>Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.
  arXiv  Detail & Related papers  (2026-01-29T03:53:25Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• 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)
• 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)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
  Large language models (LLMs) have transformed the development of embodied intelligence. This paper uncovers a significant backdoor security threat within this process. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
  arXiv  Detail & Related papers  (2024-08-06T01:20:12Z)
• A Novel Approach to Identify Security Controls in Source Code [4.598579706242066]
  This paper enumerates a comprehensive list of commonly used security controls and creates a dataset for each one of them. It uses the state-of-the-art NLP technique Bidirectional Representations from Transformers (BERT) and the Tactic Detector from our prior work to show that security controls could be identified with high confidence.
  arXiv  Detail & Related papers  (2023-07-10T21:14:39Z)

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.