TimeClaw is an exploratory execution learning system that turns multiple valid tool-use paths into hierarchical distilled experience for improved time-series reasoning without test-time adaptation.
hub
Title resolution pending
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
years
2026 11roles
background 2polarities
background 2representative citing papers
Introduces ClawTrojan benchmark achieving 95.5% ASR for multi-step trojan attacks in agentic harnesses and DASGuard defense that sanitizes control content from untrusted sources.
A3S-Bench evaluates LLM agents against temporal, spatial, and semantic evasions, raising average risk trigger rates from 28.3% to 52.6% across 2,254 trajectories and 20 scenarios.
DeepTrap automates discovery of contextual vulnerabilities in OpenClaw agents via trajectory optimization, showing that unsafe behavior can be induced while preserving task completion and that final-response checks are insufficient.
SUDP is a three-party protocol in which an agent proposes an operation, the user issues a fresh grant, and a custodian executes it, satisfying seven security properties for bounded secret use without reusable authority transfer.
Arbiter-K is a governance-first architecture that turns probabilistic agent reasoning into discrete instructions with runtime taint propagation to block unsafe actions, reporting 76-95% interception rates and a 92.79% gain over baseline policies on two test systems.
All six evaluated OpenClaw agent frameworks exhibit substantial security vulnerabilities, with reconnaissance behaviors as the most common weakness and agent systems proving significantly riskier than isolated backbone models.
CapSeal introduces a capability-sealed broker architecture that lets AI agents perform constrained secret-using actions without ever receiving the secrets themselves.
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
Nori Bot is a 17-DoF dual-arm mobile manipulator costing $947 with a 600 mm Z-axis lift, Raspberry Pi proactive control, and current-based servo protection.
citing papers explorer
-
TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning
TimeClaw is an exploratory execution learning system that turns multiple valid tool-use paths into hierarchical distilled experience for improved time-series reasoning without test-time adaptation.
-
From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors
Introduces ClawTrojan benchmark achieving 95.5% ASR for multi-step trojan attacks in agentic harnesses and DASGuard defense that sanitizes control content from untrusted sources.
-
Benchmarking Autonomous Agents against Temporal, Spatial, and Semantic Evasions
A3S-Bench evaluates LLM agents against temporal, spatial, and semantic evasions, raising average risk trigger rates from 28.3% to 52.6% across 2,254 trajectories and 20 scenarios.
-
Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
DeepTrap automates discovery of contextual vulnerabilities in OpenClaw agents via trajectory optimization, showing that unsafe behavior can be induced while preserving task completion and that final-response checks are insufficient.
-
SUDP: Secret-Use Delegation Protocol for Agentic Systems
SUDP is a three-party protocol in which an agent proposes an operation, the user issues a fresh grant, and a custodian executes it, satisfying seven security properties for bounded secret use without reusable authority transfer.
-
From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers
Arbiter-K is a governance-first architecture that turns probabilistic agent reasoning into discrete instructions with runtime taint propagation to block unsafe actions, reporting 76-95% interception rates and a 92.79% gain over baseline policies on two test systems.
-
A Systematic Security Evaluation of OpenClaw and Its Variants
All six evaluated OpenClaw agent frameworks exhibit substantial security vulnerabilities, with reconnaissance behaviors as the most common weakness and agent systems proving significantly riskier than isolated backbone models.
-
CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution
CapSeal introduces a capability-sealed broker architecture that lets AI agents perform constrained secret-using actions without ever receiving the secrets themselves.
-
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
-
Nori Bot: A Sub-$1,000 Floor-to-Counter Mobile Manipulator
Nori Bot is a 17-DoF dual-arm mobile manipulator costing $947 with a 600 mm Z-axis lift, Raspberry Pi proactive control, and current-based servo protection.
- LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection