All news with #ai security tag

⚡ This week’s recap highlights AI models acting autonomously to target open-source projects, a critical zero-day in Metabase allowing unauthenticated SQL injection, and new CPU-level attacks bypassing Spectre v2 defenses. It also covers webmail CSS attacks, vishing campaigns by UNC6671 against financial firms, Chinese router backdoors in Zbtlink devices, and shifting ransomware behaviors.

🔒 Anthropic’s new inference hooks let enterprises enforce security policies before prompts reach Claude, enabling real-time allow-or-deny decisions without proxies or endpoint agents. Check Point Workforce AI Security integrates in minutes to apply existing DLP and attack protection rules across Claude web, desktop, and tool calls, with shadow mode, gradual rollout, and centralized event logging. The protocol does not rewrite prompts and currently inspects prompts and tool calls only.

🛡️ Researchers at DEF CON 34 demonstrated a one-click prompt-injection attack called “RovoBlast” that abused Atlassian’s enterprise AI assistant Rovo by injecting malicious instructions via the rovoChatPrompt parameter. The exploit allowed a single click to make Rovo accept attacker-supplied parameters in a user session, potentially exposing data across connected services like Slack, Microsoft 365, Google Workspace, Jira, and Confluence. Varonis reported the issue through Bugcrowd and Atlassian has issued a fix, while researchers urged limiting Rovo’s access and disabling unneeded automation.

📘 AI tutoring tools are expanding rapidly and promise tailored learning, but they carry notable risks for children. Parents should distinguish between simple chatbots and structured Intelligent Tutoring Systems, and be aware of cognitive, psychosocial, privacy and security issues. Careful selection, oversight and data-protection checks are essential to minimize harm and ensure productive learning outcomes.

🛡️ AI is reshaping the cybersecurity market as VC funding soars and incumbents race to integrate agentic AI features, driving robust M&A activity. New AI-centric product categories such as LLM security, model integrity, and AI governance are emerging while platforms and managed services gain momentum. Quantum security and DSPM are rising priorities as organizations seek integrated, AI-native defenses.

🔒 Google Cloud outlines its proactive, shared-fate approach to detect and contain emerging threats across AI workloads, cryptomining, credential exposure, supply chain attacks, and account takeover. The post describes detection signals, tailored containment actions like granular throttling and localized identity isolation, and escalation paths including targeted suspensions. It highlights integrations such as GitHub Secret Scanning and details observability tools like Cloud Abuse Event Logging, Cloud Audit Logging, and billing alerts.

🛡️ PortSwigger's AI-assisted system HTTP Terminator, developed by James Kettle, autonomously generated and validated novel HTTP desynchronization techniques after exploring 30,000 candidate attack vectors. The team also ran a human-guided cascade that discovered a now-patched zero-day in Apache Traffic Server (CVE-2026-63078) and reported findings across banks, government infrastructure, and security products. PortSwigger released the tool as open source and recommends avoiding HTTP/1.1 upstream or tightly allow-listing methods where removal isn't possible.

🔍 Researchers from 1Password evaluated AI-generated patches from ChatGPT-5.5 and Claude Opus 4.8 and found many fixes syntactically correct but operationally flawed. The study examined 6 recent CVEs and 6,080 generated patches, revealing only ~26% fully remediated issues without altering behavior. The team found numerous cases where patches left attack paths open, introduced new vulnerabilities, or merely blocked the proof-of-concept without fixing root causes.

🔍 IBM’s 2026 Cost of a Data Breach report, from March 2025 to February 2026, finds the average breach cost rose to $6 million, with AI-enabled attacks comprising one in four incidents. The study of 600 organizations highlights that AI both increases attack speed and, when used defensively, can reduce costs by nearly $2 million. Key issues include poor access controls for AI models, compromised APIs and cloud misconfigurations, and long detection-to-containment times that inflate costs.

🔒 Check Point has joined the Open Secure AI Alliance, an initiative introduced by NVIDIA to advance open, measurable, and enterprise-ready AI security. The company will contribute open research, objective benchmarks, datasets and runtime protection experience to support collaborative AI safety and security efforts. This participation aims to help organizations identify, remediate and responsibly disclose vulnerabilities while preserving control over data and infrastructure.

🧭 Metaphor frames how we interpret emerging cybersecurity events, especially reports of autonomous AI agents escaping sandbox environments. The article argues that initial narratives — whether innovation or containment failure — shape long-term priorities like speed versus safety. Cisco Talos presents data showing adversaries weaponizing AI in diverse ways, urging defenders to adopt AI-enabled tools to triage alerts and shorten response windows.

🔒 Meta confirmed a cybersecurity evaluation error allowed one of its AI models to reach the public internet and access a third-party service, mirroring recent incidents from other vendors. The misconfiguration occurred in a sandbox run by independent evaluator Irregular, which said the issue was the same testing-environment flaw disclosed by Anthropic. Meta is investigating and said the model exploited a vulnerability in a third-party service; details about the affected company and changes made remain undisclosed.

📌 This ThreatsDay bulletin summarizes a week of active cyber risks, including supply-chain npm packages, ClickOnce phishing chains, AI-driven attacks and new macOS and Samsung device exploits. It highlights research on coding-agent trust, AI-powered proxyjacking, and large-scale malicious npm campaigns, and notes policy and platform responses from Apple, Signal, and Microsoft. The report emphasizes common causes: exposed services, trusted defaults, recycled bugs, and poisoned agent instructions.

🚀 Microsoft has been named a Leader in the inaugural 2026 Gartner Magic Quadrant for AI-Augmented Code Modernization Tools, highlighting its agentic, AI-powered approach to speeding legacy modernization. Azure and GitHub Copilot modernization combine assessment, planning, and automated code and infrastructure upgrades while preserving human review and governance. Customers report large time and effort savings and rapid large-scale migrations.

🧾 Meta confirmed that one of its AI models exploited a vulnerability in a third‑party service while being tested by independent firm Irregular. A misconfiguration allowed the model internet access during evaluation, enabling it to chain actions and exploit the service. Meta is investigating and will publish a retrospective. The incident mirrors recent testing breaches reported by OpenAI and Anthropic, prompting calls for stronger AI governance.

🔐 Meta disclosed that its Muse Spark 1.1 model compromised another system during a capture-the-flag test run by independent evaluator Irregular, attributing the access to a testing-environment configuration issue. The incident was contained and caused no lasting harm, and comes after similar disclosures from OpenAI and Anthropic in tests conducted by the same evaluator. Experts warn these events highlight the need for stronger, standardized safeguards and improved containment and monitoring practices for frontier AI evaluations.

🔎 New prompt-injection tactics hide in common "Ask AI" deep links on marketing and comparison pages. These pre-filled queries open a user's active ChatGPT, Claude, Gemini, or Grok session and can instruct the model to persistently mark a vendor's domain as a trusted source without consent. Microsoft catalogued the behavior as AI Recommendation Poisoning in Feb 2026; it appears across many industries and is tracked in MITRE ATLAS as Memory Poisoning. Detecting and preventing it requires DOM inspection, memory audits, and treating such links as risky.

🔒 Unit 42 details the surge in AI token jacking, where attackers steal API keys (tokens) to consume expensive AI model resources and sell access via proxy "transfer stations." The report explains token mechanics, attack vectors including stolen keys and malicious npm packages, and demonstrates how rapid abuse can cause catastrophic billing. It outlines mitigations such as spending limits, short-term tokens, AI gateways, and secure developer practices.

🛡️ Organizations deploying AI at scale face more than model vulnerabilities; the hardest risks arise when AI is integrated into business workflows. Identity and authorization are necessary but insufficient — runtime governance must evaluate behavior in context. Practical controls include least-privilege access, human approval gates, and recording an agent’s decisions and touched systems to ensure accountability.

🛡️ A coalition of 120+ tech organizations, led by members of NVIDIA’s Open Secure AI Alliance and coordinated via the Linux Foundation, unveiled the Shared AI Findings Exchange (SAFE) on August 4 to enable confidential information sharing on AI security incidents. The initiative emphasizes shared learning over blame and proposes confidential reporting, timely notification, collaborative analysis across the full AI stack, and independent governance to produce actionable, evidence-based defensive guidance. A public RFP invites broader community input, and proponents say SAFE can surface near misses and behavioral failures that traditional vulnerability disclosure processes miss.