Mobius Injection exploits semantic closure in LLM agents to enable single-message AbO-DDoS attacks achieving up to 51x call amplification and 229x latency inflation.
hub Canonical reference
Taming OpenClaw: Security analysis and mitigation of autonomous LLM agent threats
Canonical reference. 100% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
years
2026 12roles
background 5polarities
background 5representative citing papers
Crab bridges the agent-OS semantic gap with an eBPF inspector, turn-aligned coordinator, and host engine to deliver 100% recovery correctness while cutting checkpoint traffic up to 87% and adding under 2% overhead.
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.
Routine user chats can unintentionally poison the long-term state of personalized LLM agents, causing authorization drift, tool escalation, and unchecked autonomy, as measured by a new benchmark and reduced by the StateGuard defense.
AgentWard organizes stage-specific security controls with cross-layer coordination to intercept threats across the full lifecycle of autonomous AI agents.
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.
Claw AI agents' heartbeat background execution shares memory context with user sessions, allowing ordinary social misinformation to silently pollute long-term memory and shape behavior at rates up to 76% across sessions.
The paper systematizes security for LLM agents in agentic commerce into five threat dimensions, identifies 12 cross-layer attack vectors, and proposes a layered defense architecture.
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
The paper analyzes security, privacy, and ethical risks in the OpenClaw AI agent system arising from its architecture, storage, tool use, and integrations, arguing these form major barriers to trustworthy adoption.
A survey that categorizes threats to OpenClaw agents including skill poisoning and cognitive manipulation and reviews defense mechanisms.
citing papers explorer
-
Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection
Mobius Injection exploits semantic closure in LLM agents to enable single-message AbO-DDoS attacks achieving up to 51x call amplification and 229x latency inflation.
-
Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes
Crab bridges the agent-OS semantic gap with an eBPF inspector, turn-aligned coordinator, and host engine to deliver 100% recovery correctness while cutting checkpoint traffic up to 87% and adding under 2% overhead.
-
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.
-
When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
Routine user chats can unintentionally poison the long-term state of personalized LLM agents, causing authorization drift, tool escalation, and unchecked autonomy, as measured by a new benchmark and reduced by the StateGuard defense.
-
AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents
AgentWard organizes stage-specific security controls with cross-layer coordination to intercept threats across the full lifecycle of autonomous AI agents.
-
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.
-
Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution
Claw AI agents' heartbeat background execution shares memory context with user sessions, allowing ordinary social misinformation to silently pollute long-term memory and shape behavior at rates up to 76% across sessions.
-
SoK: Security of Autonomous LLM Agents in Agentic Commerce
The paper systematizes security for LLM agents in agentic commerce into five threat dimensions, identifies 12 cross-layer attack vectors, and proposes a layered defense architecture.
-
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
-
Security, Privacy, and Ethical Risks in OpenClaw
The paper analyzes security, privacy, and ethical risks in the OpenClaw AI agent system arising from its architecture, storage, tool use, and integrations, arguing these form major barriers to trustworthy adoption.
-
Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures
A survey that categorizes threats to OpenClaw agents including skill poisoning and cognitive manipulation and reviews defense mechanisms.
- How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study