Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.
Uncovering security threats and architecting defenses in autonomous agents: A case study of OpenClaw
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
baseline 2
citation-polarity summary
years
2026 11representative citing papers
SentinelAgent defines seven properties for verifiable delegation chains in multi-agent AI systems and reports a protocol achieving 100% true positive rate at 0% false positives on a 516-scenario benchmark while using TLA+ to verify six deterministic properties.
SafeClawBench supplies 600 staged adversarial tasks and three separate endpoints that show semantic acceptance, audit evidence, and sandbox-observed harm are distinct failure modes in tool-using LLM agents.
Introduces ePCA framework using neural-symbolic isolation to force agents to formalize intentions as logical constraints, claiming zero attack success and false positive rates in tested scenarios.
A new multi-turn security benchmark shows OpenClaw agents across ten LLMs trigger harmful actions in 28–53% of adversarial cases, and fragmented or file-hidden attacks roughly double baseline risk rates.
LivePI benchmark reports indirect prompt injection success rates of 10.7-29.6% across five models on seven input surfaces and shows a two-layer defense blocking all malicious completions while preserving utility.
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
A TEE-backed architecture isolates security-critical decisions in self-hosted AI agents to prevent host-level abuse from malicious inputs while maintaining allowed functionality.
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.
This work categorizes seven risks of OpenClaw for non-technical users, provides plain-language mitigations, and supplies a companion Skill to automate security configurations.
A survey that categorizes threats to OpenClaw agents including skill poisoning and cognitive manipulation and reviews defense mechanisms.
citing papers explorer
-
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.
-
SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems
SentinelAgent defines seven properties for verifiable delegation chains in multi-agent AI systems and reports a protocol achieving 100% true positive rate at 0% false positives on a 516-scenario benchmark while using TLA+ to verify six deterministic properties.
-
SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
SafeClawBench supplies 600 staged adversarial tasks and three separate endpoints that show semantic acceptance, audit evidence, and sandbox-observed harm are distinct failure modes in tool-using LLM agents.
-
Provably Secure Agent Guardrail
Introduces ePCA framework using neural-symbolic isolation to force agents to formalize intentions as logical constraints, claiming zero attack success and false positive rates in tested scenarios.
-
ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents
A new multi-turn security benchmark shows OpenClaw agents across ten LLMs trigger harmful actions in 28–53% of adversarial cases, and fragmented or file-hidden attacks roughly double baseline risk rates.
-
LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection
LivePI benchmark reports indirect prompt injection success rates of 10.7-29.6% across five models on seven input surfaces and shows a two-layer defense blocking all malicious completions while preserving utility.
-
Security Considerations for Multi-agent Systems
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
-
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation
A TEE-backed architecture isolates security-critical decisions in self-hosted AI agents to prevent host-level abuse from malicious inputs while maintaining allowed functionality.
-
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.
-
Understanding and mitigating the risks of OpenClaw for non-technical users: A practical guide with Skill
This work categorizes seven risks of OpenClaw for non-technical users, provides plain-language mitigations, and supplies a companion Skill to automate security configurations.
-
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.