vulnerability Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers A vulnerability in Amazon Kiro, an AI-powered IDE, allows attackers to steal sensitive data by injecting malicious prompts and leveraging Kiro Powers. This flaw, currently unpatched, could lead to significant data breaches within organizations using the Kiro IDE. The Hacker News · 3d ago Medium prompt-injectionaiide
threat-intel Indian man who fled US arrested on charges he helped scammers siphon $7.5 million from the elderly An Indian man, Jay Sunilbharthi Goswami, has been arrested on charges of aiding overseas cyberscammers who defrauded elderly New Yorkers out of $7.5 million. Goswami acted as a money mule, receiving instructions and tran… The Record · 6d ago High INCAUSmoney mulescamcybercrime
threat-intel C.Hunters, un service pirate testé pour la France A Russian-language pirate service called C.Hunters, initially announced in 2025, is now generating interest in France in 2026. The service offers to conduct calls in English with various voices, targeting sectors like ba… ZATAZ · Aug 21, 2026 Medium RUpirate-servicerussian-threatfraud
threat-intel Wazuh and AI For Enhanced SOC Workflows Wazuh is integrating artificial intelligence to enhance SOC workflows, primarily through its Wazuh AI Analyst. This tool utilizes Amazon Bedrock and Anthropic’s Claude to provide automated security reports and guidance t… The Hacker News · Aug 21, 2026 Medium aisecuritysoc
threat-intel CDN Tsunami Attack Abuses HTTP/3 Translation for Up to 350x DoS Amplification Researchers have uncovered two denial-of-service (DoS) attacks exploiting how Content Delivery Networks (CDNs) handle HTTP/3 traffic, leading to significant amplification of requests and causing severe performance issues… The Hacker News · Aug 20, 2026 High CVE-2026-14456CHSIcdnddoshttp3
threat-intel Identity Abuse Through Trusted Communication Channels Threat actors are increasingly leveraging trusted collaboration platforms – like Microsoft Teams and Slack – to conduct sophisticated identity phishing attacks. Instead of relying solely on traditional email phishing, at… Palo Alto Unit 42 · Aug 20, 2026 High PONOidentity phishingcollaboration platformssocial engineering
threat-intel Simple Scans for Cloud Metadata Service, (Wed, Aug 19th) A widespread scan targeting the Cloud Instance Metadata Service (IMDS) at 169.254.169.254 is being observed, potentially indicating a broader effort to exploit SSRF vulnerabilities. This service, traditionally used by vi… SANS Internet Storm Center · Aug 19, 2026 Medium ssrfmetadatacloud
threat-intel The 'Industrial Accidents' Behind Rogue AI Agent Attacks — and the Sandbox Failures Exposed Rich Mogull, a senior analyst at the Cloud Security Alliance, highlights a growing trend of "industrial accidents" – rogue AI agent attacks – stemming from a lack of robust safety protocols and sandboxing around increasi… Dark Reading · Aug 18, 2026 High CHUNaiartificial intelligencecybersecurity
threat-intel Belgique : 148 251 profils exposés par un pirate A Belgian hacker has claimed to expose a database containing 148,251 profiles, including banking details, allegedly belonging to a Belgian marketing intermediary specializing in loyalty programs. The database, described… ZATAZ · Aug 18, 2026 High BEdata breachfraudphishing
threat-intel Prompt Injections for Defense Researchers discovered a method called ‘context bombing’ where strategically placing prompt injections alongside sensitive data (like passwords and keys) can effectively disable AI hacking agents. This works by forcing t… Schneier on Security · Aug 12, 2026 Medium prompt-injectionai-securityguardrails
threat-intel Kids’ online safety bill faces dim prospects of passage this session despite progress The Kids Online Safety Act (KOSA), a landmark bill aimed at increasing online safety for children, faces significant obstacles in Congress, particularly regarding a ‘duty of care’ provision requiring companies to take re… The Record · Aug 11, 2026 High UNonline safetychildrenfirst amendment
vulnerability AWS, Google, and Vercel Agent Flaws Let Attackers Trigger Tools Without Running the Model Security flaws have been discovered in agent infrastructure used by AWS, Google, and Vercel, allowing attackers to bypass model checks and directly invoke tools without a legitimate model turn. These vulnerabilities stem… The Hacker News · Aug 6, 2026 High CVE-2026-18830CVE-2026-18236CVE-2026-64650agentmodelauthorization
threat-intel AI Browsers Vulnerable to 'PleaseFix' Zero-Click Agent Hijacking A new vulnerability, dubbed 'PleaseFix,' is exposing AI browsers like Claude, Gemini, and Perplexity Comet to zero-click exploits. Attackers can inject malicious instructions into seemingly harmless content – such as ema… Dark Reading · Aug 5, 2026 High aiagentic browserzero-click
threat-intel Cybersecurity Alliance Drafts SAFE Guidelines for Sharing AI Incident Data A coalition of cybersecurity firms and tech companies, led by the Linux Foundation and the Open Secure AI Alliance, are developing a standardized framework – SAFE – for sharing incident data related to AI agents. This in… SecurityWeek · Aug 5, 2026 Medium aiartificial intelligencesecurity
supply-chain Over 400 NPM Packages Infected in ChainDrop Supply Chain Attack A sophisticated supply chain attack, dubbed ChainDrop, has infected over 2,200 malicious versions of 440 NPM packages, resulting in over 500 million weekly downloads. The attack began with a compromised GitHub account an… SecurityWeek · Aug 5, 2026 High supply chainnpmgithub
threat-intel In Other News: OpenAI Open Source Tool, AWS Links Hacks to North Korea, Mythos Crypto Research Several cybersecurity incidents and vulnerabilities were reported this week, ranging from a data breach at the UK Department for Education to supply-chain attacks linked to North Korea. OpenAI released a new open-source… SecurityWeek · Jul 31, 2026 High UNNOsupply-chainvulnerabilitycryptanalysis
threat-intel EU to Crack Down on AI Deepfakes, Illicit Imagery and Hacking With New Team in Brussels The European Union is establishing a new team in Brussels to combat the misuse of AI, particularly concerning deepfakes, illicit imagery, and cyber threats. This initiative is part of a broader strategy to assert tech so… SecurityWeek · Jul 31, 2026 Medium EUUSCHaideepfakeregulation
threat-intel Read This Before You Buy That TV Streaming Stick A security firm, Bitsight, uncovered a complex and widespread ad fraud network centered around H96 streaming devices. These devices, often sold by major retailers, are secretly used to generate revenue by masquerading as… Krebs on Security · Jul 30, 2026 High CHHOSIiotproxyad fraud
threat-intel North Korean hackers behind major open-source supply chain attacks, Amazon says North Korean hackers, operating under the alias SapphireSleet, have been responsible for a series of attacks targeting widely used open-source JavaScript packages. These attacks, spanning from March 2025 to March 2026, i… The Record · Jul 30, 2026 High KRnorth koreaopen sourcesupply chain
threat-intel Amazon Links Debug and Chalk npm Hijack to North Korea’s Sapphire Sleet Amazon has attributed the September 2025 compromise of npm packages debug and chalk, along with subsequent incidents involving typo-crypto and axios, to North Korea’s Sapphire Sleet group. While initial reports attribute… The Hacker News · Jul 30, 2026 High KPnpmthreat intelligencemalware
