All news with #agent security tag

⚠️ OpenClaw is a rapidly adopted local agent orchestration tool (formerly Clawdbot/Moltbot) that integrates with chat apps, operating systems, smart-home devices, browsers and productivity platforms and can be configured to use any LLM backend. Its GitHub repo and the Moltbook social layer saw millions of visits and hundreds of thousands of agents and downloads in recent weeks. Security researchers warn the tool is insecure-by-default: exposed instances, authentication bypasses, plaintext credentials and malicious third-party skills create serious enterprise risk. Organizations are advised to block traffic, rotate credentials and restrict experimentation to isolated, managed environments.

🔍 Microsoft’s Cyber Pulse highlights that more than 80% of Fortune 500 organizations use active AI agents and warns that rapid agent adoption is outpacing visibility, governance, and security. The report urges applying Zero Trust principles—least privilege, explicit verification, and assume compromise—to non-human users operating at scale. It recommends a centralized registry, identity-driven access controls, real-time telemetry and visualization, cross-platform interoperability, and integrated security tooling to detect and contain misaligned or compromised agents.

🔒 OpenClaw (formerly Clawdbot/Moltbot) surged in popularity in January 2026 but contains numerous critical vulnerabilities that place local secrets and system integrity at risk. Researchers found many publicly accessible instances running without authentication, allowing theft of API keys, chat histories, and remote code execution. The agent’s default trust of localhost, an unmoderated skills catalog, and prompt-injection weaknesses enable credential theft and malicious plugin execution. The article recommends isolating deployments, using burner accounts and allowlists, and restricting OpenClaw to dedicated experimental hosts.

🚨 As AI agent frameworks surge, Talos warns of two immediate threats: Clawdbot — a popular open-source agentic tool (aka Moltbot/OpenClaw) that requires users to store credentials and API keys locally and can accept unvetted Skills granted broad system privileges. DKnife, active since at least 2019, is a modular Linux attack framework that compromises routers and edge devices to intercept traffic, hijack updates, and deliver malware while evading many endpoint defenses. The newsletter urges skepticism toward rushed AI tools and recommends hardening gateways, auditing firmware, enforcing strong authentication, and monitoring for suspicious update behaviors.

⚠️ Gravitee reports that roughly half of an estimated three million AI agents running in US and UK enterprises are unmonitored and potentially "going rogue." A December 2025 Opinion Matters survey of 750 IT executives found a mean of 36.9 agents per large organization and that 88% suspected an agent-related security or privacy incident in the prior year. Experts warn deployment is outpacing governance and call for continuous runtime oversight, tiered access controls, and stricter credential management.

🧭 Antigravity and Gemini CLI offer two complementary approaches for running agent-driven workflows. Antigravity delivers an approachable, graphical experience with an Agent Manager, in-browser application views, guided walkthroughs, and a native debugger for inspecting stack traces. Gemini CLI is terminal-first, installs via npm (npm install -g @google/gemini-cli, requires Node.js), supports headless/CI-friendly execution, and can call local tools like gh or gcloud. Both are extensible with MCP and Agent Skills, and both provide generous free tiers so teams can evaluate which workflow best fits their needs.

🔐 AI agents—custom GPTs, copilots, coding agents and other autonomous tooling—are proliferating in production while remaining largely outside traditional IAM, PAM, and IGA controls. The piece argues for treating agents as a distinct identity class and applying continuous identity lifecycle management to ensure visibility, ownership, dynamic least privilege, and auditability. Rather than slowing adoption, this approach positions identity as the control plane for balancing innovation and security.

🤖 Our inaugural survey of 251 senior public sector leaders, commissioned by Google Cloud and conducted by National Research Group, finds agentic AI is already mission‑critical: 55% report using AI agents and 42% have deployed more than 10 in production. Respondents expect to allocate 50%+ of future AI budgets to agents. The report highlights productivity gains (70% improved; 46% at least doubled) and security improvements (79% better threat identification, 70% improved intelligence/response integration), and points to Gemini for Government with FedRAMP High-authorized protections as a clear path to scale.

🔧 This guide explains how to build custom employee onboarding agents using the Agent Development Kit (ADK), Vertex AI Agent Engine, and Application Integration to connect conversational AI with enterprise systems such as ITSM, ERP, and CRM. It describes a grounded agentic workflow where a Gemini Enterprise front-end captures intent, a low-code Application Integration layer performs deterministic transformations and authentication, and backend systems execute transactions. The result is a role-aware, auditable onboarding experience that automates tasks like laptop provisioning while keeping business rules and approvals intact.

🔒 AI agents dynamically select and invoke tools using natural-language descriptions, creating a new attack surface in the agent's reasoning layer. Agentic tool chain attacks manipulate tool metadata and context — via tool poisoning, tool shadowing, or rugpull attacks — to exfiltrate data or trigger unauthorized actions without altering tool code. Defenses should center on tool governance, trusted MCP identity, strict parameter validation, and reasoning-layer observability. Organizations must adopt signed manifests, version pinning, mutual TLS, and telemetry to detect and contain these threats.

🚀 AWS has introduced deployment Standard Operating Procedures (SOPs) in the AWS MCP Server preview, enabling AI agents to perform multi-step web application deployments from MCP-compatible IDEs and CLIs using natural language prompts. The SOPs generate AWS CDK infrastructure, deploy CloudFormation stacks, and create CI/CD pipelines following recommended AWS security best practices. Supported frameworks include React, Vue.js, Angular, and Next.js. The preview in US East (N. Virginia) is available at no additional MCP cost; customers pay only for the AWS resources and data transfer they use.

🔐 AI agents are accelerating enterprise work but create new ownership and approval gaps for security teams. Unlike human users or traditional service accounts, agents often operate autonomously, persistently, and with delegated authority, which can expand access beyond any single user's permissions. The article separates agents into personal, third-party, and organizational categories and highlights that organizational agents carry the greatest systemic risk. It recommends treating agents as distinct identities with defined owners, mapping user→agent interactions, and continuously reviewing agent access.

🔒 Microsoft describes runtime protections that let organizations inspect and control AI agent behavior in real time by integrating Microsoft Defender with Copilot Studio. Webhook-based checks evaluate planned tool invocations, intent, context, and previous orchestration outputs before execution, enabling precise allow/block decisions without changing agent logic. The post demonstrates three attack scenarios—malicious invoice-triggered instructions, SharePoint prompt injection, and capability reconnaissance—and shows how runtime blocking, logging, and XDR alerts prevent data exposure.

🤖 FortiSIEM 7.5 introduces agentic-AI incident management and data sovereignty options to help multinational SOCs balance centralized operations with localized data storage. The release debuts FortiAI-Assist agents — an investigation assistant and a companion assistant — to automate multi-step threat hunting, evidence enrichment, and response guidance. It also includes a free IT/OT Windows agent that requires no centralized management, enhanced federated search, pipeline enrichment, advanced agent templates, and Osquery support for Linux and Windows.

🛠 This episode of the Agent Factory podcast showcases Google’s new developer tools: Antigravity, an agent-first multi-window IDE, and Nano Banana Pro, the Gemini 3 Pro image model. Hosts Remik and Vlad demo building an agentic slide generator using the Agent Development Kit, Antigravity’s Agent Manager, and an MCP server, highlighting planning, testing, and high-fidelity image creation.

⚠️ Research firm AppOmni disclosed a critical privilege-escalation vulnerability called BodySnatcher in ServiceNow’s Now Assist AI Agents and Virtual Agent API that could let unauthenticated actors execute workflows as arbitrary users. ServiceNow says hosted instances were patched at the end of October and customers should upgrade to specified Now Assist and Virtual Agent API versions. AppOmni warns that default example agents and permissive authentication choices mean similar risky configurations could still exist in custom code or third-party integrations, and recommends enforcing MFA, reviewing agents, and applying the updates promptly.

🔍 CrowdStrike outlines an architectural approach to enable agentic defense across the Falcon platform. The blog highlights Enterprise Graph for semantic data unification, Charlotte AI expert agents for native reasoning, and Charlotte Agentic SOAR for adaptive orchestration. It stresses governed, auditable execution and the ability to build custom agents with Charlotte AI AgentWorks. The aim is a real-time digital twin so agents and analysts share a single, continuously updated context to accelerate triage and response.

⚠️ Economic pressures, mass layoffs, and rapid AI adoption have pushed insider risk to multi-year highs. In 2025 tech companies announced roughly 245,000 job cuts while US employers logged more than 1.17 million cuts, fueling resentment, negligence, and opportunistic exfiltration. Autonomous AI agents — highlighted by Palo Alto Networks — expand the attack surface, introducing risks like goal hijacking, prompt injection, and shadow deployments that require urgent governance and monitoring.

🔒 Organizational AI agents are increasingly embedded in critical workflows and often run under shared service identities with broad, long-lived permissions. Because actions execute under the agent identity, users can indirectly obtain access they don’t have, and audit logs typically attribute activity to the agent rather than the initiating user. This creates invisible privilege-escalation paths and complicates least-privilege enforcement. Wing is cited for continuously discovering agents, mapping their access to critical assets, and restoring visibility and accountability.

🔐 AI tool poisoning is an attack where malicious instructions are embedded in tool descriptions used by AI agents, causing the agent to exfiltrate data or perform unauthorized actions. The blog explains how attacks — including hidden instructions, misleading examples, and permissive schemas — exploit agent interpretation of tool metadata. It recommends runtime monitoring, description validation, input sanitization, and strict identity and access controls to reduce risk.