AgentPhishing: A Benchmark of LLM Email Agents Under Adaptive Attack

Summary

AgentPhishing is a benchmark that tests whether persuasive phishing emails can evade detection and get LLM email agents to comply with malicious requests. Its PhishOpt method optimizes reusable email-generation skills against individual agents, and the authors build a universal skill from persuasion-principle analysis. In an evaluation of nine agents, four had phishing-detection rates below 10% and malicious-request compliance rates above 45%.

Related items

• InfoDiffusion Language Models for Perplexity-Aware Black-Box AttacksSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoHarmful Responses Are Jailbreak Templates: Transferring Autoregressive Jailbreaks to Diffusion Language ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoIs Claude Code safe for the enterprise? What the official settings cover, and what they don'tSimilar attack · Adversa AI Blog
• InfoEnterprise Agentic RAG with Pre-Search Role-Based Access Control, Multi-Layered Guardrails, and Operational TelemetrySimilar attack · OpenAlex (peer-reviewed AI security)
• InfoMirage: Targeted Jailbreaks Against Post-Generation Safety Checkers in Multimodal Diffusion ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)