When Approval Becomes Execution: Authorization-Grounded Workflow Attacks on Tool-Using Agents

Tool-using language-model agents increasingly rely on local services for document access, approval management, and enterprise workflow execution. This paper studies an authorization-grounded workflow attack in the OpenClaw Agent Security Attack Competition, a controlled benchmark derived from...

Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents

Tool-using agents read untrusted external content, which exposes them to indirect prompt injection IPI, where hidden instructions hijack the agent's tool calls. Benchmarks measure IPI security by the attack success rate ASR, which treats every failed attack as a successful defense. To test this...

CreepScope: Measuring Post-Use Authorization Exposure in Tool-Using Agents

Authorization checks at individual tool calls do not reveal how long earlier authority remains usable. We study this lifecycle failure as privilege creep: a capability stays reachable after its last justified workflow step. We present CreepScope, a trace-oriented evaluation protocol that samples...

SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents

Language-model agents increasingly use tools to act on external systems. Earlier actions can alter files, permissions, database records, or other state, making a later routine-looking action harmful. Yet the visible interaction may not reveal the underlying state needed to assess that action. We...

MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current red-teaming. First, mode collapse in attack generation,...