SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants

• URL: http://arxiv.org/abs/2603.28807v1
• Date: Sat, 28 Mar 2026 05:03:54 GMT
• Title: SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants
• Abstract summary: SafeClaw-R is a framework that enforces safety as a system-level invariant over the execution graph.<n>We evaluate SafeClaw-R across three domains: productivity platforms, third-party skill ecosystems, and code execution environments.
• Score: 10.897758061443989
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal data and services, but this autonomy introduces significant safety and security risks. Unintended actions from LLM reasoning failures can cause irreversible harm, while prompt injection attacks may exfiltrate credentials or compromise the system. Our analysis shows that 36.4% of OpenClaw's built-in skills pose high or critical risks. Existing approaches, including static guardrails and LLM-as-a-Judge, lack reliable real-time enforcement and consistent authority in MAS settings. To address this, we propose SafeClaw-R, a framework that enforces safety as a system-level invariant over the execution graph by ensuring that actions are mediated prior to execution, and systematically augments skills with safe counterparts. We evaluate SafeClaw-R across three representative domains: productivity platforms, third-party skill ecosystems, and code execution environments. SafeClaw-R achieves 95.2% accuracy in Google Workspace scenarios, significantly outperforming regex baselines (61.6%), detects 97.8% of malicious third-party skill patterns, and achieves 100% detection accuracy in our adversarial code execution benchmark. These results demonstrate that SafeClaw-R enables practical runtime enforcement for autonomous MASs.

Related papers

• OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills [14.078280127843108]
  Third-party skills can contain latent safety risks that only emerge during actual execution.<n>In this work, we conduct a systematic investigation into how well current agent systems recognize and avoid such risks.<n>To support quantitative and qualitative evaluation, we construct OpenSkillRisk, a dedicated safety benchmark containing 263 risky skills.
  arXiv  Detail & Related papers  (2026-07-22T13:24:09Z)
• Trust but Verify? Uncovering the Security Debt of Autonomous Coding Agents [3.30025498453752]
  This paper presents a large-scale empirical study using the AIDev dataset to characterize security code smells in agent-generated pull requests.<n>We find that 38.9% of agent-generated PRs contain at least one security smell, with supply chain integrity issues accounting for 82.3% of all detected security smells.<n>Human collaborators are responsible for introducing 67.6% of genuine leaked secrets within these agent-assisted systems.
  arXiv  Detail & Related papers  (2026-07-14T06:59:41Z)
• 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)
• On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment [54.30690671490447]
  Existing safety-alignment signals are largely response-level or off-policy.<n>FATE transforms verifier-scored failures into repair supervision without expert demonstrations.<n>FATE reduces attack success rate by 33.5%, harmful compliance by 82.6%, and improves external trajectory-safety diagnosis by 6.5%.
  arXiv  Detail & Related papers  (2026-05-12T09:56:28Z)
• 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)
• The Verifier Tax: Horizon Dependent Safety Success Tradeoffs in Tool Using LLM Agents [1.3299507495084417]
  We study how runtime enforcement against unsafe actions affects end-to-end task performance in multi-step tool using large language model (LLM) agents.<n>We identify model dependent interaction horizons (15 to 30 turns) and decompose outcomes into overall success rate (SR), safe success rate (SSR), and unsafe success rate (USR)
  arXiv  Detail & Related papers  (2026-03-18T16:16:34Z)
• Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework [0.6015898117103067]
  Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety.<n>This research addresses this gap by establishing a standardized vulnerability assessment framework and developing a multi-layered defensive system to protect against identified threats.
  arXiv  Detail & Related papers  (2026-03-17T20:32:06Z)
• 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)
• 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)
• 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)
• The Dark Side of LLMs: Agent-based Attacks for Complete Computer Takeover [0.0]
  Large Language Model (LLM) agents and multi-agent systems introduce security vulnerabilities that extend beyond traditional content generation to system-level compromises.<n>This paper presents a comprehensive evaluation of the LLMs security used as reasoning engines within autonomous agents.<n>We show how different attack surfaces and trust boundaries can be leveraged to orchestrate such takeovers.
  arXiv  Detail & Related papers  (2025-07-09T13:54:58Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents [58.65256663334316]
  We present SafeAgentBench -- the first benchmark for safety-aware task planning of embodied LLM agents in interactive simulation environments.<n>SafeAgentBench includes: (1) an executable, diverse, and high-quality dataset of 750 tasks, rigorously curated to cover 10 potential hazards and 3 task types; (2) SafeAgentEnv, a universal embodied environment with a low-level controller, supporting multi-agent execution with 17 high-level actions for 9 state-of-the-art baselines; and (3) reliable evaluation methods from both execution and semantic perspectives.
  arXiv  Detail & Related papers  (2024-12-17T18:55:58Z)
• Safety Margins for Reinforcement Learning [53.10194953873209]
  We show how to leverage proxy criticality metrics to generate safety margins. We evaluate our approach on learned policies from APE-X and A3C within an Atari environment.
  arXiv  Detail & Related papers  (2023-07-25T16:49:54Z)

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.