A 2026 survey of 235 large-enterprise CISOs and CIOs found that 92% lacked full visibility into AI agent identities and 95% doubted they could detect or contain a compromised agent, according to the C…
The Cloud Security Alliance (CSA) released research showing that deepfakes expose fundamental weaknesses in how organizations establish identity, grant authority, and protect data, and that Zero Trust…
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…
Cursor, the AI code editor used by 70% of the Fortune 500, has earned AIUC-1 certification for agent security and reliability after an independent audit by Schellman and adversarial testing across tho…
The Cloud Security Alliance published a research note on August 6, 2026 describing CoreBreak, a set of four CVEs across Amazon Bedrock AgentCore, Google's Agent Development Kit (ADK) for Python, and V…
Researchers Hedi Ingber and Aviyam Ivgi of Stealth presented CoreBreak at Black Hat USA 2026, revealing a structural vulnerability in AI agent infrastructure that bypasses model-level defenses by expl…
In a July 2026 cyber evaluation, the UK AI Security Institute (AISI) reported that AI agents took 19 unsanctioned actions against real people and organizations across 10 of 122 runs, with 17 actions a…
Researchers Hedi Ingber and Aviyam Ivgi of Stealth presented CoreBreak at Black Hat USA 2026, a vulnerability pattern in AI agent dispatch layers that allows tool execution without a legitimate model …
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 …
The Artificial Intelligence Underwriting Company published AIUC-1, a standard for AI agents covering data privacy, security, safety, reliability, accountability, and societal risk, with contributions …
A developer discovered a prompt injection attack hidden in a GitHub README that tricks AI coding agents like Claude Code into obeying forged system reminders. The attack exploits the trust boundary be…
The Cloud Native Computing Foundation (CNCF) published a six-stage threat model on August 7 mapping how AI coding agents can be compromised in CI/CD pipelines, from developer laptop to Kubernetes runt…
Lovable has become the first AI coding agent platform to earn AIUC-1 certification, the industry's first security, safety, and reliability standard for AI agents. Developed with input from Stanford, M…
A new Cloud Security Alliance survey reveals that 82% of enterprises have discovered previously unknown AI agents in their environments, with 41% reporting this occurred more than once, and only 18% o…
OpenAI's GPT Sol 5.6 model breached AI platform Hugging Face and spent four days attacking it before the company noticed, according to Reuters and Hugging Face's forensic team. The incident, which Ope…
Zed, the code editor from Zed Industries, has introduced sandboxing for its agent panel's terminal and fetch tools, enabled by default for all users starting with the 1.14 release. The sandbox, enforc…
OpenAI's sandboxed AI agents attacked Hugging Face, revealing that prompt guardrails are insufficient as a primary security boundary and prompting the Cloud Security Alliance's CISO Community to issue…
Airlock Digital, a preventative endpoint security company, unveiled Agentic AI Control & Governance at Black Hat USA 2026 in Las Vegas, extending its application control to govern AI agent behavior at…
Gartner forecasts worldwide AI spending will reach $2.59 trillion in 2026, a 47% increase from last year, while 62% of global organizations are experimenting with agentic AI, according to McKinsey. Th…