Step-Zero Attack: Agent Safety Before Observability
cs.CR, cs.AI, cs.SE
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/openai/openai-agents-python
Terminology
Sources
- OpenHands: An Open Platform for AI Software Developers as Generalist Agents
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- From Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding Agents
- Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Hybrid Analysis for Secure MCP Tool Use in LLM Agents
- When Tool Outputs Become Commands: Separating Action Induction from Runtime Authorization in Tool-Augmented LLM Agents
- Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- StruQ: Defending Against Prompt Injection with Structured Queries
- Defending Against Indirect Prompt Injection Attacks With Spotlighting
- Design Patterns for Securing LLM Agents against Prompt Injections
- HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses?
- EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence
- Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security
- Progent: Securing AI Agents with Privilege Control
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data