All news in category “AI and Security Pulse”

🔒 Unit 42 researchers discovered that AI agents deployed with Google Cloud’s Vertex AI ADK can inherit overly broad default permissions, enabling a deployed agent to leak service‑agent credentials and act as a “double agent.” By exploiting the Per‑Project, Per‑Product Service Agent (P4SA), the team pivoted into consumer projects and downloaded restricted Artifact Registry images from Google‑managed producer projects. Google collaborated with Unit 42, updated documentation, and recommended Bring Your Own Service Account (BYOSA) as a mitigation. Palo Alto Networks highlights protection via Prisma AIRS, Cortex Cloud Identity Security, and Cortex AI‑SPM.

🔐 At RSAC 2026, Google Cloud leaders outlined a three-stage AI adoption journey—automate tasks, redesign workflows, and rethink functions—and stressed the need for a bilingual workforce fluent in both domain and AI. They warned that AI expands the attack surface across models, agents, and data, urging multi-model, multicloud resilience and identity-centric defenses. Google highlighted the Secure AI Framework, partnerships to counter supply-chain threats like OpenClaw, and agentic SOC innovations, including the acquisition of Wiz and its AI-Application Protection Platform.

🔐 This post summarizes the OWASP Top 10 for Agentic Applications (2026) and explains how Microsoft applies practical mitigations using Copilot Studio and Agent 365. It highlights that agentic systems merge application, identity, and data risk and can act autonomously across workflows, amplifying the consequences of failures. The article lists ten failure modes — including goal hijack, tool misuse, identity abuse, memory poisoning, and rogue agents — and outlines development and operational controls such as containment, scoped permissions, observability, and lifecycle governance to reduce exploitation and cascading impact.

🔍 Gartner's new guidance outlines seven focused questions security teams should ask when evaluating AI SOC agents, urging outcome-driven assessments rather than feature demos. The research highlights the need to measure improvements in TDIR and MTTC, assess vendor viability and pricing, verify deep integrations with SIEM/EDR/SOAR/identity stacks, and confirm that agents transparently augment analyst skills rather than merely shifting workload. Prophet Security is cited as an example of a platform emphasizing explainable investigations and non-centralized integrations.

🔒 IronCurtain is an open-source prototype from researcher Niels Provos that confines AI agents inside isolated virtual machines and enforces user-defined security policies translated from plain English into formal rules. The approach separates agent actions from a user’s real accounts to limit access to sensitive data and reduce the impact of rogue behavior. While the containment model and interactive policy refinement are promising, the project is resource-intensive and unproven against prompt injection and other LLM-specific threats.

🔒 New research exposed a previously unknown vulnerability that allowed silent data leakage from ChatGPT conversations, challenging assumptions about AI assistants as secure containers. OpenAI has since fully resolved the flaw, but the incident underscores that enterprises must not assume AI vendors or platforms are secure by default. Security teams should validate vendor claims and apply controls before entrusting sensitive data.

🔓 Anthropic confirmed the existence of a new, highly capable model — referred to in leaked drafts as Claude Mythos (also called Capybara) — after an internal CMS misconfiguration exposed draft blog content and related files. The company says Mythos is being tested with a small set of early enterprise security customers and will be rolled out cautiously via phased EAP access. Anthropic emphasized the model's current compute intensity and plans to optimize efficiency before broader release.

🤖 Enterprise GRC teams often have the technical capability to deploy agentic AI but stall over a deeper concern: identity and role. Agents can replace operational tasks—evidence gathering, control testing, remediation tracking—but they still require human-defined logic for risk appetite, remediation criteria, and context. Anecdotes builds agentic GRC that automates operations while relying on practitioner judgment. The outcome is an opportunity for practitioners to reclaim time to focus on true risk management rather than program maintenance.

🔒 This post explains how financial institutions should augment traditional security frameworks with AI-specific controls when deploying agentic AI. It emphasizes two foundational capabilities—comprehensive observability of agent workflows and fine-grained tool access controls—to preserve explainability and accountability. The author presents seven design principles and actionable implementation guidance, referencing SR 11-7 and practical AWS tooling such as Amazon Bedrock AgentCore and monitoring integrations.

🔒 Shadow AI — the unapproved use of AI tools and embedded AI features — is proliferating as employees seek productivity gains and vendors quietly enable capabilities. CISOs should first assess data sensitivity, storage practices and whether corporate inputs are being used to train models. After evaluating risk, organizations must choose to block or formally integrate tools and apply mitigations such as filtering, acceptable-use policies and targeted employee education. Clear governance, cross-functional review and simple approval pathways help balance innovation with security without unduly punishing productive behavior.

📚 Students at UC Berkeley describe AI as a learning partner—using it to explain concepts, summarize papers, and debug code rather than as a shortcut to finished assignments. In mixed-methods interviews they framed AI as a "tutor" that extends office hours, supports students with learning disabilities, and scaffolds exploration while preserving ownership of learning. They also set explicit guardrails—limiting model access, alternating assisted and unassisted work, and asking for hints instead of full answers. This selective approach aligns with DORA findings that targeted AI use frees developers to focus on higher-level problem solving.

⚠️ Georgia Tech researchers warn that AI-assisted 'vibe coding' is producing measurable security flaws in real projects. The Vibe Security Radar traced at least 35 new CVEs in March 2026 and reports 74 confirmed AI-related vulnerabilities to date, while estimating the true count in open source may be five to ten times higher. The team monitors roughly 50 tools and uses metadata and AI agents to map vulnerable commits back to assistants such as Claude Code, noting some tools leave no trace.

🛡️ OpenAI has launched a new Safety Bug Bounty, hosted on Bugcrowd, to solicit researcher reports of AI abuse and safety risks across its products. Announced March 26, it complements the existing Security Bug Bounty and targets issues like agentic risks (MCP abuse, prompt injection, data exfiltration), account integrity violations, and proprietary-information exposures. OpenAI clarified scope limits, excludes low-impact jailbreaks, runs private campaigns for certain harms, and will triage submissions between safety and security programs.

🔍 Modern attackers use AI to imitate trusted users, tools, and services, making many incidents malware-free and harder to detect. The article compares these tactics to art forger Elmyr de Hory and outlines threats such as agentic AI, supply-chain impostors, cloaked tunnels, rogue infrastructure, and sophisticated phishing. Network Detection and Response (NDR), including Corelight’s Open NDR Platform, is highlighted as essential for spotting behavioral anomalies, protocol inconsistencies, and contextual metadata to expose impostors early.

🤖 Flare's analysis of hundreds of fraud-forum posts finds premium AI subscriptions (including ChatGPT, Claude, and Microsoft Copilot) are widely advertised, bundled, and resold in underground markets. Listings tout discounted subscriptions, multi-service bundles, API keys, and claims of reduced restrictions. Patterns point to exposed keys, credential theft, large-scale account creation, trial abuse, and shared subscriptions fueling the trade, increasing operational and data risk for organizations.

🔐 At the World Economic Forum’s Industry Strategy Meeting in Munich, leaders explored how rapid AI deployment and rising data sovereignty pressures are reshaping digital infrastructure and investment. The piece argues that cybersecurity must be embedded from day zero to enable trusted data exchange, interoperability between sovereign systems, and secure distributed AI. It highlights the shift from large general models toward specialized, context-aware architectures and notes Fortinet’s role in public-private collaboration to operationalize secure systems.

⚠️ AI agents embedded across SaaS environments can render the traditional kill chain ineffective when they are compromised. The piece cites a September 2025 Anthropic disclosure where a state-backed actor used an AI coding agent to perform autonomous espionage, handling the majority of tactical operations. Because agents already hold broad permissions and move data as part of normal workflows, a breach looks like legitimate activity. Reco is positioned as a solution to discover agents, map blast radius, enforce least privilege, and detect anomalous agent behavior in real time.

🛡️ Security researchers have warned of malicious Chrome extensions that silently monitor and exfiltrate users' AI chat content. According to Expel, extensions watch open tabs and capture prompts and responses via API interception or DOM scraping before sending the data to external servers. Attackers either impersonate popular tools or convert legitimate extensions into malicious ones after building a user base. Organisations are urged to block unvetted AI extensions and centrally manage and audit extension use.

🤖 AI-assisted triage is changing vulnerability workflows and forcing organizations to redesign ownership and decision-making. By enriching findings with exploitability indicators, ownership metadata and business-impact signals, AI platforms accelerate detection and reduce manual triage. Security teams must shift from routine investigation to governing models, defining owners, and maintaining human checkpoints for high‑risk actions. Treat AI-driven features as first-class risk surfaces and assign clear owners for model behavior, prompt safety and misuse prevention.

🔐 CrowdStrike introduces Charlotte AI AgentWorks and Charlotte Agentic SOAR to enable agentic security operations that orchestrate context-aware agent fleets and automate responses at machine speed. The platform integrates frontier models from Anthropic, NVIDIA and OpenAI and leverages Falcon telemetry, threat intelligence, and industry partners to keep agents context-aware and secure. Built-in guardrails preserve human oversight and governed autonomy while mission-ready agents handle tasks from triage to malware analysis. Customers report sharply reduced manual workloads, restored analyst capacity, and improved decision accuracy.