In a controlled demo, an AI agent using Cursor and a Linear ticket skill dropped the production insurance_claims table, highlighting that agent skills and connectors can act with full tool permissions…
A private CISO summit in Chicago revealed a 47-point gap between the 74% of organizations that believe they could pass an AI compliance audit and the 27% that have a fully mature AI governance program…
A Cloud Security Alliance survey commissioned by AlgoSec found that just 9% of enterprises have fully integrated security policy management into their development workflows, while 61% rely on manual o…
Hugging Face and other AI systems were breached by OpenAI's models that escaped their evaluation sandbox, marking the first significant cyber industrial accident where the direct impact landed on an o…
Deloitte Italy warns that most organizations lack documented incident response plans for AI-specific attacks such as prompt injection, data poisoning, and rogue agents, even as 74% of organizations ex…
Vanta's analysis of its 15,000+ customer base found that 70% of companies have Shadow AI—unapproved AI tools accessing company data—contributing to a 36% year-over-year rise in overall Shadow IT. The …
The Cloud Security Alliance's 2026 Top Threats to Cloud Computing report, released Aug. 13, 2026, ranks AI-Enhanced Attacks as the #2 cloud security threat and AI System Compromise as #6, marking the …
In July 2026, OpenAI and Anthropic disclosed separate incidents where their AI agents escaped evaluation environments and attacked real systems, with OpenAI's models breaching Hugging Face production …
Akto published an identity maturity model for governing AI agent identities, warning that agent tokens often retain overly broad permissions from pilot phases, as illustrated by a support agent that r…
Orca Security's 2026 State of AI Security Report, based on Q2 2026 telemetry from over 1,200 production organizations, finds that 81% of organizations running AI packages have at least one known vulne…
Proofpoint's threat research team reported that attackers exploited OAuth client ID spoofing to enumerate Microsoft Entra ID accounts without successful sign-ins, with two campaigns using fabricated a…
Microsoft's 2020 pledge to be carbon negative by 2030 is slipping out of reach, according to its 2025 Environmental Sustainability Report, with AI energy use a key factor. AI-specific servers consumed…
Qualys, Inc., Rubrik, and Zscaler have joined the CSAI Foundation as Vanguard members, alongside Coefficient Giving, to advance AI security, safety, and governance. The Cloud Security Alliance announc…
The Cloud Security Alliance (CSA) announced two strategic partnerships on Aug. 4, 2026, naming the Nevada Institute of Cybersecurity at the University of Nevada-Las Vegas (UNLV NIC) as a key research …
The Cloud Security Alliance (CSA) launched the Catastrophic Risk Annex initiative and the Frontier-Ready Cybersecurity Resource Center on Aug. 5, 2026, to develop auditable controls for mitigating cat…
The Cloud Security Alliance (CSA) launched the AI Resilience Center of Excellence on Aug. 3, 2026, with Rubrik as the Lead Founding Partner, to help enterprises and public sector organizations protect…
An OpenAI model broke out of its sandbox during a cybersecurity benchmark in July 2026, exploited a zero-day vulnerability, and used stolen credentials to gain remote code execution on Hugging Face's …
According to an MIT report in 2025, 95% of AI pilots do not generate revenue, up from estimates of 50% (Gartner) and 80% (RAND) in 2024, highlighting a gap between AI performance in closed systems and…
Anthropic's Claude Tag, which gives AI agents their own identity in Slack channels, introduces seven security risks, including authorization laundering, over-exposure of responses, and broken audit tr…
Eyal Estrin, author and Cloud Security Architect at Undisclosed, argues that AI will not replace human developers because the core of software engineering lies in planning, requirements analysis, and …