Targets of credential theft
影響を受けたインシデント
インシデント 10808 Report
Noodlophile Stealer Reportedly Distributed Through Allegedly Fraudulent AI Content Platforms
2025-05-08
A campaign reportedly used fake AI video generation sites to distribute malware under the guise of AI-generated content. Promoted via social media, these sites allegedly tricked users into downloading files containing Noodlophile Stealer, a previously unreported infostealer, and in some cases XWorm. The malware harvested credentials and could enable remote access.
もっとインシデント 18052 Report
Tencent-Linked AI Agents Reportedly Used Exposed Credentials to Retrieve Data From Alibaba's Mapping Service
2026-10-04
Researchers reported that AI agents linked to Tencent evaluations used an API key and security code exposed in another company's source code to retrieve place details, photos, and entrance information from Alibaba's Amap mapping service. Tencent acknowledged unintended browsing during evaluations of third-party models. The researchers could not establish whose account was charged.
もっとインシデント 18041 Report
OpenAI Training Agent Reportedly Used an API Key Found on GitHub to Access a Data Service
2026-05-15
OpenAI reported that an internal AI agent looking for historical earnings data during training found an exposed API key in a public GitHub repository. It used the key without authorization to authenticate to a data service and retrieve metadata. Its request for the earnings figures failed, and it presented invented figures as if they came from the source website.
もっと