arXiv AI By Nicholas Saban

Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

Read the original on arXiv AI →

arXiv:2606. 05233v1 Announce Type: cross Abstract: Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%, but these headline numbers cluster on retired models and on the most-vulnerable model in each paper's panel.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jun 2

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

arXiv:2606. 02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls.

By Hiskias Dingeto, Will Leeney
arXiv AI
Jun 11

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

arXiv:2605. 23243v2 Announce Type: replace-cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM-R, across C/Java/Python) and black-box web application security testing (five production-style applications with 118 ground-truth vulnerabilities across 20+ CWE families, which we will open-source).

By Vivek Dahiya, Sunny Nehra, Vipul Dholariya, Bhavik Shangari, Chandra Khatri
arXiv AI
Jun 18

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.

By Yuchuan Tian, Mengyu Zheng, Haocheng Mei, Ye Yuan, Chao Xu, Xinghao Chen, Hanting Chen, Yu Wang