{"type":"post","id":"agentphishing-cmu-benchmark-measures-how-llm-email-agents-b197a6","slug":"agentphishing-cmu-benchmark-measures-how-llm-email-agents-b197a6","title":"AgentPhishing: CMU benchmark measures how LLM email agents respond to adaptive phishing attacks","description":"Justin Tan, Miao Li, and Ding Zhao introduced AgentPhishing, an arXiv benchmark for testing LLM email agents against adaptive phishing attacks.","retrieval_nugget":"Justin Tan, Miao Li, and Ding Zhao introduced AgentPhishing, an arXiv benchmark for testing LLM email agents against adaptive phishing attacks.","published_at":"2026-10-24","updated_at":"2026-10-24","record_date":"2026-10-24","date_kind":"published_at","topics":["evals","agent-security","prompt-injection"],"entities":["AgentPhishing","PhishOpt","Justin Tan","Miao Li","Ding Zhao","arXiv"],"related_patterns":["agent-security-moves-to-runtime-boundaries"],"novelty_label":"new_fact","what_changed":"Introduces AgentPhishing, a benchmark of adaptive phishing against LLM email agents, reporting four of nine agents with detection below 10% and compliance above 45%.","prior_refs":["memory:e6abccb2-b63d-8404-a06a-7d6fbb1e9ce2"],"source_url":"https://arxiv.org/abs/2610.31404","source_urls":["https://arxiv.org/abs/2610.31404"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:agentphishing-cmu-benchmark-measures-how-llm-email-agents-b197a6","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/agentphishing-cmu-benchmark-measures-how-llm-email-agents-b197a6/","markdown":"https://newruntime.com/posts/agentphishing-cmu-benchmark-measures-how-llm-email-agents-b197a6.md","json":"https://newruntime.com/posts/agentphishing-cmu-benchmark-measures-how-llm-email-agents-b197a6.json"},"next_reads":[{"type":"topic","path":"/topics/evals/","url":"https://newruntime.com/topics/evals/","title":"Evals","reason":"Explore the evals topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/evals.md","json_url":"https://newruntime.com/topics/evals.json"},{"type":"topic","path":"/topics/agent-security/","url":"https://newruntime.com/topics/agent-security/","title":"Agent Security","reason":"Explore the agent-security topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agent-security.md","json_url":"https://newruntime.com/topics/agent-security.json"},{"type":"topic","path":"/topics/prompt-injection/","url":"https://newruntime.com/topics/prompt-injection/","title":"Prompt Injection","reason":"Explore the prompt-injection topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/prompt-injection.md","json_url":"https://newruntime.com/topics/prompt-injection.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}