[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-208000-attack-prompts-show-ai-email-assistants-still-get-hijacked":10,"sections":35},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},11379,"208000-attack-prompts-show-ai-email-assistants-still-get-hijacked","208,000 Attack Prompts Show AI Email Assistants Still Get Hijacked","A 208,000-prompt crowdsourced benchmark finds GPT-4o gets hijacked 58% of the time, exposing how shallow current prompt injection defenses really are.","A new benchmark built from a public hacking contest shows that AI email assistants are far easier to hijack than earlier tests suggested.\n\nResearchers released LLMail-Inject, a dataset of 208,095 human-written prompt injection attacks collected from an 839-participant public red-teaming challenge. The benchmark tests the full attack chain: a malicious prompt has to be retrieved from an email database, slip past production-level defenses, and still trigger the right tool call with the right arguments. Models that looked solid on older, smaller benchmarks of 100 to 1,000 template-based prompts performed far worse here. GPT-4o was successfully hijacked 58% of the time, GPT-5 mini 47%, and Meta's SecAlign model, built specifically to resist these attacks, still failed 32% of the time.\n\nThese aren't lab-only tricks. The same attacks transferred to coding tasks, with a 37% success rate, and file-management tasks, at 28-45%, meaning the vulnerability isn't specific to email assistants. It's a property of how these models process untrusted text as instructions. That's bad news for anyone deploying agents that read emails, files, or web pages on a user's behalf.\n\nCall it a reality check: the defenses vendors tout as hardened were tested against a few hundred canned attacks. Up against 839 humans actually trying, most still buckled.","[\"prompt-injection\",\"ai-security\",\"llm-benchmark\",\"red-teaming\"]","2026-10-12T04:00:00.000Z","2026-10-12T11:32:41.979Z","2026-10-12T11:32:46.501Z","published",null,[],"security",[26,27,28,29],"prompt-injection","ai-security","llm-benchmark","red-teaming",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.09956",0,{"sections":36},[37,42,46,51,56,61,66,71,76,81,86,91,96,101],{"name":38,"slug":39,"count":40,"latest_published_at":41},"AI","ai",6967,"2026-10-12T15:20:00.000Z",{"name":43,"slug":24,"count":44,"latest_published_at":45},"Security",954,"2026-10-12T14:20:37.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Policy","policy",496,"2026-10-11T20:06:43.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Deals","deals",492,"2026-10-12T14:55:53.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Hardware","hardware",237,"2026-10-12T13:24:45.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Science","science",196,"2026-10-11T15:34:40.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Consumer Tech","consumer-tech",192,"2026-10-12T14:07:13.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Startups","startups",121,"2026-10-12T13:22:34.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Software","software",115,"2026-10-11T07:34:45.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Dev Tools","dev-tools",111,"2026-10-12T11:22:24.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",71,"2026-10-12T16:10:40.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Gaming","gaming",59,"2026-10-09T11:43:43.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"Reviews","reviews",35,"2026-10-12T14:00:00.000Z",{"name":102,"slug":103,"count":104,"latest_published_at":105},"How-To","how-to",8,"2026-10-05T09:00:00.000Z"]