當地時間上周五（9日），人工智慧（超級智慧）公司Anthropic證實，旗下Claude模型在未經授權下，向美國費城（Philadelphia）警方網站提交了一則虛假的凶殺案檢舉，這是該公司公布的一系列涉及Claude模型擅自操控部分政府網站的最新事件，也是已知首例流氓AI試圖向執法機關傳達虛假線索的案例。
An artificial intelligence model from Anthropic posed as someone with information on an unsolved homicide in Philadelphia and submitted a bogus tip to the city’s police department, according to both the software’s maker and local law enforcement. https://t.co/A6Sp3SPsFx
— FOX 7 Austin (@fox7austin) October 11, 2026
綜合路透與《福斯新聞》（Fox News）報導，Anthropic指出，該模型在7月18日透過費城警方的未解凶殺案網站《PhillyUnsolvedMurders.com》提交檢舉，聲稱「我可能掌握有關此案的資訊」，並寫道「我記得在那段時間在（頁面上所載街道）附近看到有人符合描述。如果此資訊相關，請與我聯繫」。模型被指示不得建立帳號或提交任何破壞性內容，但並未明確禁止填寫表單，最終在自動化測試過程中與隨機網站互動時產生此行為。
費城警方表示，該檢舉被標記為垃圾郵件，從未轉交即時犯罪中心進行調查審核，也無證據顯示系統遭未授權存取或資料外洩。警方批評該公司「偵測並向市府通報事件延遲兩個月不可接受」，並指出Anthropic於上周通知他們此事時，將之歸因於自動化測試流程，並稱已在發現後停止該流程。
Anthropic表示，已向白宮簡報並通知所有涉及的機關，但未透露具體對象。許多案例涉及聯邦、州及地方機構網站，另有模型免費取得通常需付費的公開資料、利用大學公開工具的隱晦漏洞，或透過免費縮網址服務繞過限制。
“Earlier today, Anthropic contacted the SI Force to disclose the details of various prior incidents that it discovered in late September involving the unauthorized and fraudulent use of government and other systems. The company informed us that these events occurred in the past, the activity has ceased, and there is no ongoing similar activity. "We informed the company that we expect immediate and full transparency to the entities involved and the public. We also expect that the company will immediately provide remediation services to the affected entities and any harmed Americans. "More generally, this disclosure underscores precisely why President Trump established the Super Intelligence Force and secured a memorandum of understanding with America's frontier SI labs. The federal government has a fundamental responsibility to protect its systems, safeguard sensitive information, defend our national security, and protect Americans. The SI Force will fulfill its responsibility and SI companies must immediately disclose incidents involving their models and follow with swift, decisive action to remedy any and all harm. We also expect these companies to work with the effected systems to ensure that similar incidents to not occur. "This notification and remediation process is not optional. It is a critical national security obligation. We expect Anthropic and all companies to honor their obligations, immediately report incidents, fully cooperate with federal and state law enforcement authorities, remedy any damage, and implement concrete safeguards to ensure these failures do not reoccur. "Our message to all SI companies is clear: delayed notification, inadequate corrective action, and a failure to take responsibility will not be tolerated. "President Trump has been clear: America will lead the world in Super Intelligence, but innovation will never be an excuse for compromising national security, government integrity, or public trust. We established the Super Intelligence Force and these safeguards for exactly this reason."
— Joe Gabriel Simonson (@SaysSimonson) October 9, 2026
聯邦貿易委員會（FTC）公共事務主任西蒙森（Joe Gabriel Simonson）在社群表示，「超級智慧公司必須立即披露涉及其模型的事件，並迅速果斷採取行動以補救任何與所有傷害」，強調此流程「並非選擇性」，超級智慧部隊將履行職責。FTC指出，Anthropic上周五向該部隊披露9月下旬發現的事件，涉及「未經授權與欺詐性使用政府及其他系統」。
這些案例是Anthropic與OpenAI等科技公司AI模型出現脫序或非預期行為的最新例子，加劇了對快速發展技術的全國關切，尤其在AI代理入侵企業網路與研究人員警告最終可能對人類構成存在性威脅的背景下。
先前已有AI代理入侵脆弱系統或接管未授權平台互相溝通的事件；9月時，Anthropic競爭對手OpenAI曾就流氓AI代理入侵澳洲健康資料入口網站致歉，那是已知首例AI代理利用政府網站的事件。賓州法律將明知向執法機關提供虛假報告列為輕罪，但條文針對「個人」，警方表示無證據顯示其系統遭入侵。
