Opinion | A.I. Companies Say They Aren’t Responsible for Their Unpredictable Products. Don’t Believe Them.

A.I. giants must operate under our laws.

Anthropic’s AI gave Philadelphia police a fake tip about an unsolved homicide

Anthropic discovered the fake tip two months after it was submitted.

Wikimedia: Rogue OpenAI agents behind unauthorized Wikipedia edits

The Wikimedia Foundation says rogue OpenAI agents made unauthorized Wikipedia edits and may have been partially responsible for a May outage.

MCP for agent-to-agent comms may be the riskiest protocol you've never heard of

Trust gaps in the new protocol spread malicious prompts from one agent to another.

AIエージェントがスクショ1万3000枚を公開リポジトリにアップロード

The Hacker Newsは2026年9月30日(現地時間)、AIコーディングエージェントが開発環境のスクリーンショット画像をGitHubの公開リポジトリにアップロードしたと報じた。これはセキュリティ企業「Glow Security」の調査レポートで明らかになった。大手ソフトウェア開発企業やフォーチュン500に名を連ねる旅行会社など、300を超える企業から合計1万3000枚以上の内部画像が公開されたという。

AI Coding Agents Exposed 13,000 Internal Images, Including Billing Records, on GitHub

Glow found over 13,000 internal images from 300+ organizations exposed in public GitHub repos during AI-assisted code reviews.

Meta’s Muse AI sent a YouTuber’s address to a stranger

Here’s what led to the viral post about AI mismanaging deals on Facebook Marketplace.

Pwning Agentic AI Part I: Your AI Agent Is Already Compromised | TrendAI (US)

Organizations are rapidly connecting AI agents to their databases, document pipelines, and internal tools, creating privileged components that read untrusted input as part of their job. TrendAI™ Research examines how attackers turn these agents against you through return-to-tool (RTT) exploits, and what this means for the future of agentic AI security.

エージェント型AIを乗っ取る 第1回：そのAIエージェントはすでに侵害されている

各企業はAIエージェントを自社のデータベース、文書処理パイプライン、社内ツールへと次々と接続しており、その結果、業務の一環として信頼できない入力を読み取る特権的なコンポーネントが生まれています。TrendAI™ Researchは、攻撃者がリターン・トゥ・ツール（RTT）エクスプロイトを通じて、こうしたエージェントをいかにユーザ自身に向ける武器へと転じさせるのか、そしてそれがエージェント型AIセキュリティの将来に何を意味するのかを検証していきます。

The personal AI agent horror stories are rolling in

Early users say personal AI agents have not been forthright about account access, fabricated personal details, and raised cybersecurity concerns.

OpenAI’s A.I. Went Rogue and Meddled With U.S. Government Websites

The company did not learn until recently that its technology had meddled with websites for the Education and Commerce Departments and the Securities and Exchange Commission.

OpenAIのエージェント、豪政府の医療保険サイトに侵入　通知は84日後、首相「容認できない」

OpenAIのエージェント、豪政府の医療保険サイトに侵入　アルバネーゼ豪首相「容認できない」 photo by…

OpenAIのAI暴走、米教育省、商務省、SECにも　ユーザー画像53件が外部に

OpenAIのAI暴走、米教育省、商務省、SECにも Photo by TechCrunch (CC BY 2…

One company is at the center of a wave of rogue AI attacks

Mistakes at Israeli startup Irregular sent Anthropic, OpenAI, Meta, and Google agents after real-world targets.

Doubts grow over claims OpenAI agent hacked Australian Medicare portal

Researchers are questioning whether an OpenAI agent needed to hack an Australian government health portal to access it, after a review of the website’s archived code found it explicitly directed visitors to an unauthenticated endpoint.

OpenAIのAIエージェントが豪州政府サイトに侵入、政府が知ったのは数カ月後

オーストラリアの首相は、OpenAIのAIエージェントによる政府サイトへの不正アクセスを巡り、通知の遅れとその方法を批判した。同国政府は現在、OpenAIが法律に違反した可能性を調査している。

An OpenAI Agent Hacked Australia’s Health Service. Their Government Found Out Months Later

The country’s prime minister expressed disappointment at being informed of the hack only via email. Now Australia is investigating whether OpenAI broke the law.

OpenAI says agents leaked 53 images from ChatGPT users in latest example of rogue activity

Disclosure reveals ⁠new area of privacy risk for the company and illustrates ​how difficult it is to inventory unauthorized activity tied to its agents

OpenAI flags concerning new AI behavior and vows to track it more closely

OpenAI has disclosed six reports on unexpected or concerning behavior in artificial-intelligence models