APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
cs.CR, cs.CL
Submitted: 2026-10-09
Updated: 2026-10-09
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Defeating Prompt Injections by Design
- Kimi K3: Open Frontier Intelligence
- It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
- AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
- OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
- APEX-Agents
- Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
- The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents
- LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs