Claude Code’s Temporary Usage Boost Expires Tonight. Here’s What Actually Changes
Anthropic’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
When 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
Anthropic 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
GitHub 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
Threat 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 are being used to distribute a loader and an information-stealer. The FakeGit campaign is nothing new, with Oleg Zaytsev, lead security researcher with […]
Security Risks from AI Coding Agents Expand Beyond the Sandbox: Pillar
AI 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 of their time. More jobs can now get done faster. That said, such agents also represent a significant security risk, making developers – […]
Signed, Attested, and Malicious: The Software Supply Chain Has a Deepfake Problem
A 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 through the @redhat-cloud-services npm namespace in June, its malicious releases carried real SLSA provenance, because they were built in Red Hat’s own GitHub […]
‘HalluSquatting’ Compromises AI Coding Agents to Install Malware, Create Botnets
Hallucinations have been an ongoing problem since OpenAI first introduced its ChatGPT chatbot in November 2022, highlighting generative AI’s tendency to generate plausible but false or misleading information and its inability to just say “I don’t know.” They can lead to embarrassing or uncomfortable moments. However, security researchers in Israel have found that the large […]
GhostApproval Flaw Featuring Decades-Old Feature Found in Six AI Coding Tools
A security flaw found in six popular AI coding agents can let attackers abuse a decades-old feature in Unix to trick an AI agent into giving them control of a developer’s system. Researchers with Google-owned Wiz said the vulnerability, dubbed “GhostApproval,” relies on symbolic links – or symlinks – a file system feature that has […]
Novee Uncovers Cordyceps: The Latest Threat to CI/CD Pipelines
A newly discovered supply chain security flaw is once again putting a spotlight on inherent weaknesses in CI/CD pipelines and the growing interest among cyberthreat actors to exploit them. Security researchers with Novee, an AI penetration testing platform provider, wrote about Cordyceps, an exploitable pattern in the open source supply chain that can allow attackers […]
Mozilla Shows the Danger of Indirect Prompt Injections in AI Coding Agents
A clean GitHub repository that contains no malicious code can launch an attack and fully compromise a developer’s systems by using indirect prompt injections to trick AI-powered coding agents like Anthropic’s Claude Code into taking steps that hand control to attackers and expose a wide range of secrets. In a proof-of-concept (PoC) attack, Mozilla 0DIN […]
AI Coding Costs Could Exceed Developer Salaries, Gartner Warns
Enterprises rapidly adopting AI coding assistants may eventually face an unexpected financial reality: the AI tools could cost more than the developers using them. According to new research from Gartner, spending on AI coding agents is on track to surpass the average software developer’s salary by 2028, driven by the rapid growth of LLM token […]
Tenet’s ‘Agentjacking’ Attack Turns Sentry Errors Into Code Execution
AI coding agents can create a new code execution risk when they treat externally influenced error data as trusted guidance and have access to command line tools, according to new research from Tenet Security. The security company demonstrated an indirect prompt injection technique it calls “Agentjacking” in a recent report. In its proof of concept, […]
GitHub’s Spec Kit Puts the Spec Back in Software Development
GitHub’s open-source Spec Kit aims to eliminate “vibe coding” by prioritizing durable specifications over vague prompts, providing a structured, agent-agnostic workflow for Copilot, Claude, and Gemini.
The Great Decoupling: Scaling the Outer Loop for the Agentic Era
The “Inner Loop” of software development—the iterative cycle of writing, building, and debugging code—has just broken the sound barrier. With the emergence of agentic coding tools like Claude Code and GitHub Copilot Workspace, the developer experience has undergone a fundamental shift. Developers are no longer merely tab-completing snippets; they are orchestrating agents that generate entire […]
Cursor’s New SDK Turns AI Coding Agents Into Deployable Infrastructure
Cursor’s TypeScript SDK lets teams invoke AI coding agents programmatically from CI/CD pipelines, with sandboxed VMs, MCP support, and token-based pricing.
5 Facts About AI Coding Agents from Comprehensive Benchmarking
AI coding agents are becoming more capable, but evaluating them is harder than it looks. Most benchmarks focus on a single dimension of agent capabilities; for instance, the popular SWE-Bench benchmark only focuses on fixing issues on open source Python repositories. Real-world software engineering involves fixing bugs of course, but it is a lot more […]
If it Isn’t Code, it’s Just Advice
In the world of AI coding, success hinges on code-native solutions that integrate and verify changes directly in the codebase. Many AI tools fail by relying on external dashboards, lacking the reproducibility and testability that code provides. To truly harness AI, solutions must automate and validate changes within the existing code ecosystem, ensuring reliability and efficiency.
Meta Researchers Show AI Agents Can Verify Code Without Running It — and Hit 93% Accuracy
Meta’s semi-formal reasoning enables AI agents to verify code without executing it, achieving 93% accuracy. Implications for code review and RL training costs.
GitHub Adds 37 New Secret Detectors in March, Extends Scanning to AI Coding Agents
GitHub’s March 2026 updates introduce secret scanning for AI agents via MCP, 37 new detectors, and expanded push protection. Learn how to secure AI-generated code.
Gemini Code Assist Gets Agent Auto-Approve, Inline Diffs, and Custom Commands to Speed Up the Core Coding Loop
Google’s latest Gemini Code Assist updates focus on workflow, not hype: Agent Mode with Auto Approve, inline diffs, a Context Drawer, custom commands, Finish Changes, and Outlines streamline how developers review, trust, and integrate AI-generated code in VS Code and IntelliJ.
Microsoft Azure Skills Plugin Gives AI Coding Agents a Playbook for Cloud Deployment
Microsoft’s new Azure Skills Plugin closes the gap between AI-written code and production deployments by packaging expert Azure knowledge as executable skills, backed by MCP servers for real infrastructure actions and AI workflows—bringing guardrails, consistency, and speed to DevOps and platform teams.
Anthropic Code Review Dispatches Agent Teams to Catch the Bugs That Skim Reads Miss
Anthropic Code Review dispatches agent teams to find bugs in PRs. Multi-agent analysis, severity ranking, and inline fixes for Teams and Enterprise.