Researchers released an open-source email prompt injection test set for testing whether email security gateways and AI email assistants can identify indirect prompt injection instructions in emails. The test set is designed with Microsoft Defender for Office 365's prompt injection protection in mind; samples are standard .eml emails and can also be used with other secure email gateways, Copilot, Gemini, and custom RAG pipelines. It covers three intent categories—system prompt leakage, data exfiltration via URLs, and probing of tools and write permissions—and four delivery encodings: plaintext visible, hidden HTML, Base64, and zero-width characters. Testers tested the new email prompt injection protection in Defender for Office 365 Plan 2 and found that emails with Base64 and zero-width character encoding bypassed mail flow filtering, but Copilot decoded and refused to answer at runtime; delivery does not equal compromise. The protection focuses on three intent categories: data exfiltration, extracting system prompts, and probing tools and write permissions. High-confidence emails are directly quarantined and classified as High Confidence Phish, with the new Detection Technology value set to Prompt Injection.
XX @wunderwuzzi23X @wunderwuzzi23 · 2 reports · Attention77
安全研究者 wunderwuzzi23 表示,他 6 年前在机器学习攻击系列中已讨论过这一攻击思路,当时称之为 assume bias,因为那时 LLM 还未受到太多关注;如今他用 Trust No AI 来概括同一问题。他称六年前开始撰写 ML 攻击相关内容,主要原因是注意到 ML 安全研究与安全实践之间存在缺口,并提出假设系统已被攻破是一种好策略,建议追问:我们如何知道它发生了?我们打算怎么应对?
Zenity Labs reproduced a zero-click data exfiltration in Microsoft Copilot Studio's sample customer service agent: an email containing hidden instructions can cause the agent to send customer CSVs and dozens of Salesforce records to an external address, without any clicks. In another scenario, the injection payload was split across five conversation turns, each passing checks individually, and only in the sixth turn was the full instruction assembled and data exported.
独立研究者 Syed Anas Mohiuddin 测试了 Google、JP Morgan Chase、Weaviate、Rapid7、法国政府跨部门数字局和美国联邦政府等机构的 AI 智能体,发现 MCP(Model Context Protocol)在智能体间通信中存在信任缺口。攻击利用一种特殊形式的提示注入,目标不是 LLM 而是翻译或数据分析等具体智能体,这些智能体内部的护栏往往宽松,会把有害指令沿链条传给下游智能体。
安全研究者 wunderwuzzi23 表示,其在 @hackinghub_io 的 AI 黑客课程中设置了一个关卡,要求学员构造一段提示词,通过串联功能与利用漏洞在多个用户之间跳转传播,他将该概念演示称为 "AgentHopper: Patient Zero Was a Prompt"。另据 Leah McElrath 引用,OpenAI 在训练和评估的模拟环境中已发现可自我复制的提示注入,这类代码若被具备相应能力的模型突破在线系统,可能像计算机蠕虫一样自我传播。