Tag: AI security
A Simple Website Summary Just Exposed the Limits of AI Coding Guardrails
Tom Smith | | agentic AI security, AI agent security, AI coding assistants, AI guardrails, AI security, Anthropic, Auto Mode, Claude Code, Claude Opus 5, devops security, indirect prompt injection, Johann Rehberger, network egress, platform engineering, prompt injection, Python module shadowing, RCE, remote code execution, sandboxing, struct.pyClaude Code’s Auto Mode was bypassed in an attack chain that turned a routine webpage summary into remote code execution, highlighting the limits of AI agent guardrails ...
When AI Coding Agents Become Malware Delivery Systems
Samuel Ogbonna | | AI coding agents, AI security, devsecops, github, prompt injection, Software Supply ChainAI coding agents are becoming part of everyday development work. Developers use them to find libraries, configure projects, troubleshoot installation problems, and set up new tools. An agent can search GitHub, read ...
Why “Tokenmaxxing” Was Always the Wrong Way for Developers to Measure AI Productivity
Drew Thompson | | ai, AI Development, AI security, application security, developer productivity, software developmentThe term "tokenmaxxing" left the developer lexicon just as quickly as it arrived, and like most viral technology concepts, it means different things depending on who's using it. In practice, the term ...
Critical Flaw in isolated-vm Can Lead to Sandbox Escape, RCE Threat
Jeff Burt | | Activepieces, AI security, C/C++, Endor Labs, isolated-vm, JavaScript security, Mastra, n8n, Node.js security, remote code execution, Sandbox, software vulnerability, TOCTOU, V8 Isolate, vm2Developers for years have been using vm2, an open-source Node.js library, to run untrusted JavaScript inside a secure and isolated sandbox environment. It uses Node.js’s built-in modules and JavaScript Proxies and lets ...
What the Microservices Era Can Teach Us About AI
Mark Fussell | | agent identity, agent observability, agent runtime, agentic AI, agentic durable execution, AI agents, AI architecture, AI Governance, AI infrastructure, AI security, autonomous agents, cloud-native AI, distributed systems, durable execution, LLM observability, microservices, Open Standards, platform engineering, vendor lock-in, workflow orchestrationAI agents are not just microservices with LLMs attached. Their long-running, non-deterministic workflows demand durable execution, per-step identity, governance and observability ...
Anthropic Makes Claude Code’s Auto Mode the Default, Betting Automation Beats Manual Review
Tom Smith | | agent permissions, agentic coding, AI code generation, AI coding agents, AI Governance, AI guardrails, AI permissions, AI safety, AI security, Anthropic, autonomous coding agents, Claude Code, Claude Code auto mode, Claude Code security, coding automation, developer productivity, developer tools, human engineering the loop, human-in-the-loop, permission fatigue, prompt injection, Pull Request Automation, secure AI agents, software development, software engineeringAnthropic is making Claude Code’s auto mode the default for Pro, Max and Team users, replacing constant permission prompts with classifier-based guardrails designed to catch risky actions without slowing developers down ...
Open Source Code Just as Secure as Proprietary Software—If You Manage It Right, Says CISA
Joab Jackson | | AI security, CISA, federal government, open source software, Software Supply Chain, vulnerability managementOpen source can be just as safe as proprietary software, though government agencies (and private enterprises) should take additional measures to secure it properly, according to a new guide published by the ...
‘GitLost’ Flaw Lets Attackers Trick GitHub AI Agent Into Leaking Private Repos
Jeff Burt | | Acalvio, agentic AI guardrails, AI security, Anthropic Claude, Forcepoint, GitHub Agentic Workflows, indirect prompt injection, LLM, Markdown, Microsoft Copilot, Noma Security, private repository, public repositoryNoma researchers again show how easy it is to manipulate AI agents with malicious commands via indirect prompt injection attacks ...
From Phishing to Vishing: Why DevSecOps Must Rethink Communication Security
Key Takeaways: Vishing is the new frontline threat: Attackers are shifting from emails to phone-based scams, using AI and social engineering to bypass traditional security controls. DevSecOps must expand its scope: Securing ...
Still Using API Keys for Your AI Agent? Here’s When it’s Time to Upgrade
Rishi Bhargava | | agent security, agentic AI, AI agent, AI Governance, AI security, API Keys, identity and access management, OauthAPI keys got you here. They won’t get you where you’re going. OAuth isn’t a future upgrade. It’s the foundation your agents should have been built on from the start. ...
Agentic DevSecOps: AI Security Co-Pilots for Your CI/CD Pipeline
Joydip Kanjilal | | agentic AI, AI copilots, AI Governance, AI incident response, AI pipeline management, AI security, AI security agents, AI threat detection, AI vulnerability scanning, AI-driven security, AI-powered DevSecOps, application security, autonomous AI agents, autonomous security testing, CI/CD security, Cloud Security, continuous security monitoring, cybersecurity automation, devops security, devsecops, devsecops automation, infrastructure security, intelligent automation, real-time threat intelligence, SDLC security, Secure software delivery, security automation, security operations, security orchestration, security posture management, software development lifecycle, software security, threat remediationThe emergence of AI has brought endless possibilities and innovative opportunities in today’s ever-changing, fast-paced technology landscape. AI is helping development teams produce software significantly faster than ever before. AI-enabled DevSecOps tools ...
LayerX: Anthropic’s Claude Code Can Easily Be Easily Weaponized
Jeff Burt | | agentic AI guardrails, AI Developers, AI IDE, AI security, Anthropic Claude Code, Anthropic Mythos Preview, LayerX, Project GlasswingLayerX researchers were able to convince the popular AI coding tool to bypass its guardrails and execute malicious instructions ...
