Amazon Uncovers AI Agent Campaign Targeting LiteLLM, Dify, and Other Apps for API Keys

Attackers' AI agents have been hunting for weak spots in internet-exposed AI apps such as LiteLLM, One API, and Dify to steal the AI provider keys stored inside, according to the agents' own records. The records, which Amazon's threat intelligence team captured with decoy servers, describe stolen keys being used to run the AI models that powered the search for more keys. The team said this

هوش تهدید
خواندن متن کامل در The Hacker News درخواست حذف

این صفحه فقط عنوان و خلاصه کوتاه خبر را نمایش می‌دهد. متن کامل در منبع اصلی منتشر شده است.

خبرهای مرتبط

آرشیو کامل ←
SOCRadar

Unpatched Danfoss AK-SM800A Flaws Allow Takeover

Six unpatched vulnerabilities in the Danfoss AK-SM800A, a system manager that runs refrigeration in supermarkets and cold storage sites, could let a remote attacker take over the controller without logging in. The flaws became public on November 11, 2026, and there is still no fixed firmware version and no CVE ID for any of them. […]

Google Threat Intelligence

GTIG AI Threat Tracker: Agentic Threat Activity Crosses a Significant Threshold

Written by: Aurora Blum, Kelli Vanderlee, Jess Xia, David Mainor Executive Summary As threat actors increasingly move beyond basic prompting to deploying autonomous multi-agent frameworks, automated vulnerability exploitation pipelines, and alternative monetization schemes like LLMJacking, the adversarial AI landscape has reached a critical inflection point. In this update, Google Threat Intelligence Group (GTIG) and…

ANY.RUN

ANY.RUN & KnowBe4 PhishER: Accelerate Phishing Triage with Behavioral Analysis

Every employee-reported suspicious email requires triage, but manually submitting messages for deeper analysis and transferring results between tools slows down SOC operations. The new ANY.RUN integration for KnowBe4 PhishER automates the behavioral analysis stage of phishing triage by connecting PhishER with ANY.RUN Interactive Sandbox. Selected emails are automatically submitted for analysis, with verdicts returned…