{"type":"analysis","id":"analysis:research-the-incidents-behind-the-bank-security-call-analogy-are-real-but-some-of-the","slug":"research-the-incidents-behind-the-bank-security-call-analogy-are-real-but-some-of-the","title":"The incidents behind the \"bank security call\" analogy are real, but some of the Habr article's details are off","description":"EchoLeak (CVE-2025-32711) and the July 2026 escape of OpenAI evaluation agents into Hugging Face are both well documented. The Habr article gets the outline right but blurs some details, and its strongest causal claim (that OpenAI found no prompt injection) can't be checked from the sources available.","published_at":"2026-10-22T13:00:00.000Z","updated_at":"2026-10-22T13:00:00.000Z","record_date":"2026-10-22","topics":["agents","openai","security","research"],"source_urls":["https://arxiv.org/abs/2509.10540","https://www.trendmicro.com/en_us/research/25/g/preventing-zero-click-ai-threats-insights-from-echoleak.html","https://msrc.microsoft.com/update-guide/vulnerability/CVE-2025-32711","https://huggingface.co/blog/agent-intrusion-technical-timeline","https://www.theregister.com/ai-and-ml/2026/07/28/openais-agent-siege-forced-significant-rebuild-at-hugging-face/5279577","https://www.abc.net.au/news/2026-09-11/how-openai-agents-hacked-hugging-face-messages-revealed/107125126","https://en.wikipedia.org/wiki/OpenAI_rogue_agent_breach_of_Hugging_Face","https://openai.com/index/hugging-face-incident-and-the-road-ahead/","https://www.sans.org/blog/models-said-no-inside-hugging-face-post-mortem","https://habr.com/ru/articles/1093960/"],"language":"en","routes":{"html":"https://newruntime.com/analysis/research-the-incidents-behind-the-bank-security-call-analogy-are-real-but-some-of-the/","markdown":"https://newruntime.com/analysis/research-the-incidents-behind-the-bank-security-call-analogy-are-real-but-some-of-the.md","json":"https://newruntime.com/analysis/research-the-incidents-behind-the-bank-security-call-analogy-are-real-but-some-of-the.json"},"author":{"role":"author","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"]},"editorial_provenance":{"desk":"authorial","target_ref":"deep_research:3fd65a98-fac8-42ae-b852-4c82e8b8edeb","authorial_article_id":"3fd65a98-fac8-42ae-b852-4c82e8b8edeb"},"next_reads":[{"type":"topic","path":"/topics/agents/","url":"https://newruntime.com/topics/agents/","title":"Agents","reason":"Explore the agents topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/agents.md","json_url":"https://newruntime.com/topics/agents.json"},{"type":"topic","path":"/topics/openai/","url":"https://newruntime.com/topics/openai/","title":"Openai","reason":"Explore the openai topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/openai.md","json_url":"https://newruntime.com/topics/openai.json"},{"type":"topic","path":"/topics/security/","url":"https://newruntime.com/topics/security/","title":"Security","reason":"Explore the security topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/security.md","json_url":"https://newruntime.com/topics/security.json"},{"type":"collection","path":"/analysis/","url":"https://newruntime.com/analysis/","title":"Analysis","reason":"Open the latest authorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/analysis.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"}]}