Tag: AI coding agents
GitHub’s August Outages Show Growth Is Outpacing Infrastructure
Tom Smith | | AI coding agents, capacity planning, CI/CD, cloud infrastructure, developer infrastructure, developer productivity, devops, distributed systems, github, GitHub Actions, GitHub Copilot, GitHub outages, incident response, platform engineering, platform reliability, production resilience, retry storms, service availability, software delivery, Software Supply ChainGitHub's August 2026 report details five outages tied to Actions and Copilot growth outpacing infrastructure. Here's what platform teams should know ...
Flaw in DeepSeek Harness AI Coding Tool Let Agents Disable Their Sandbox
Jeff Burt | | agentic AI security, AI coding agents, AI sandbox, API Keys, DeepSeek Harness, OX Security, VulnCheckNews of the now-fixed vulnerability comes amid growing concerns that AI vendors do not in have complete control of their autonomous agents ...
GitHub Puts Guardrails on Copilot’s Sandbox Inside JetBrains IDEs
Tom Smith | | AI agents, AI coding agents, AI Governance, Copilot sandbox, Developer Security, developer tools, Enterprise AI, filesystem controls, GitHub Copilot, GitHub Copilot JetBrains, IDE security, JetBrains, managed policies, MCP governance, network controls, OpenTelemetry, platform engineering, sandbox security, software developmentJetBrains IDEs are where a lot of enterprise backend work happens — Java, Kotlin, Spring, big monorepos with a lot to break. So when an AI coding agent starts running shell commands ...
From the Horse’s Mouth: Anthropic Says AI Has Changed the SDLC
Alan Shimel | | agentic development, AI code review, AI coding agents, AI Governance, AI-assisted development, AI-native SDLC, Anthropic, autonomous agents, CI/CD, Claude Code, Code Generation, developer productivity, devops, internal developer platforms, platform engineering, software delivery, software development lifecycle, software engineering, software security, software testingAnthropic’s AI-native SDLC playbook argues that faster coding is shifting the bottleneck to planning, testing, governance, deployment and operations ...
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 ...
Claude Code’s Temporary Usage Boost Expires Tonight. Here’s What Actually Changes
Tom Smith | | AI agents, AI coding agents, AI coding costs, AI coding tools, AI subscription pricing, Anthropic, CI pipelines, Claude Code, Claude Code usage limits, developer productivity, devops, Fable 5, software development, token limits, weekly usage capsAnthropic’s temporary 50% increase to Claude Code weekly usage limits expires August 19, reducing available capacity for developers and DevOps teams without lowering subscription prices ...
The Agent Proposes, the Pipeline Disposes: Controls for AI-Authored Change
Veera Ravindra Divi | | agent permissions, agentic coding, AI change control, AI code review, AI coding agents, AI Governance, AI pull requests, AI software development, AI-authored code, AI-generated code security, autonomous coding agents, bounded-write agents, change-budget gates, CI/CD security, human-in-the-loop, in-toto, independent evals, least-privilege, policy as code, protected paths, provenance attestation, provenance verification, Secure DevOps, signed attestations, Sigstore, SLSA, Software Supply Chain Security, staged autonomyWhen agents write code and open pull requests faster than humans can read them, ‘the diff looked fine’ stops being a control. The durable controls live outside the agent’s reasoning loop ...
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 ...
GitHub Brings Stacked Pull Requests Out of the Shadows
Tom Smith | | AI coding agents, branch protection, code quality, code review, continuous integration, developer productivity, DevOps workflows, gh-stack, GitHub Copilot, GitHub public preview, GitHub stacked pull requests, merge queues, pull request size, software engineering, Stacked PRsGitHub introduces native stacked pull requests, helping development teams break large changes into smaller, dependency-ordered PRs that are faster and easier to review ...
FakeGit Targets AI Coding Agents with Malicious GitHub Repos
Jeff Burt | | AgentBaiting, AI coding agents, AI supply chain risk, Anthropic Claude Code, fake repositories, FakeGit, github, Google Gemini, Island, MCP Server, OpenAI ChatGPT, SmartLoader, StealCThreat actors continue to find new ways to incorporate AI into schemes aimed at luring developers into downloading malware from fake repositories. The latest example involves almost 7,600 malicious GitHub repositories that ...
Security Risks from AI Coding Agents Expand Beyond the Sandbox: Pillar
Jeff Burt | | AI code assistants, AI coding agents, AI Developers, AI sandbox, AI security risks, Cursor, Cymulate, Google Antigravity, Google Gemini, OpenAI Codex, Pillar Security, prompt injectionAI coding assistants have become an essential part of developers’ work, automating many of the repetitive tasks – think boilerplate coding and scaffolding – that in the past ate up a lot ...
Signed, Attested, and Malicious: The Software Supply Chain Has a Deepfake Problem
Nigel Douglas | | AI coding agents, AntV packages, behavioural analysis, continuous scanning, dependency security, Developer Security, GitHub Actions compromise, malicious packages, Miasma worm, Mini Shai-Hulud, npm malware, OIDC tokens, open source security, package provenance, package quarantine, policy as code, Red Hat npm attack, registry scanning, Shai-Hulud worm, SLSA provenance, software attestation, Software Supply Chain Security, TanStack compromise, trusted pipeline attacksA developer pulls a package from a reliable repo. It is signed, has provenance, and has been scanned. And then…it contains malware. That is no longer hypothetical. When the Miasma worm tore ...
