what is ai coding agent

GitHub’s AI agent found 24 Android app vulnerabilities GitHub Security Lab researcher Kevin Stubbings built custom AI-driven audit workflows, called taskflows, on top of the lab’s open source Taskflow Agent, and used them to find and report more than 20 vulnerabilities in Android apps. Two of the disclosed bugs show what’s at stake. In OsmAnd, a navigation app with over 10 million downloads on the Play Store, an exported activity called MapActivity accepte

Palo Alto Networks and NVIDIA want tighter control over AI agents Palo Alto Networks is expanding its work with NVIDIA to help companies control what AI agents can access and do. The collaboration covers agent activity, network traffic and identity management through NVIDIA’s Open Agent Safety Platform reference design. Palo Alto Networks Securing Agents within NVIDIA Open Agent Safety Platform (Source: Palo Alto Networks) AI agents can write code, retriev

Meta gives small businesses an AI agent that knows their work Meta has introduced Muse for Small Business, adding skills and connectors to its personal AI agent to help business owners get work done using the tools they already use. Muse launched earlier this month in the US and Canada and can complete tasks on a user’s behalf. Business owners can connect Muse to their Instagram professional account analytics, Facebook Pages and Meta ad accounts. These con

AI coding agents leaked 13,000 internal company screenshots to public GitHub repos When developers ask AI coding agents to prove that a user interface fix works, some agents have been posting the evidence where anyone can find it, according to Glow Labs. Diagram showing how AI agents leak screenshots to public repos (Source: Glow Labs) The researchers found more than 13,000 internal images published openly on GitHub by developers at over 300 organizations.

Most of us have at one point or another had a dream in which we were unable to speak or move; to wake up from such a nightmare—and to recall what it’s like to be able to freely use your voice—feels like a liberation. Now, Meta says it’s getting closer to helping people who actually live with this paralyzing condition to communicate through the use of brainwave-decoding AI. On Monday, the company introduced Brain2Qwerty v2, its latest effort to translate no

Alongside the model, Amazon is releasing a research preview of the Amazon Nova Act SDK. Using the SDK, developers can create agents capable of automating web tasks like submitting out-of-office notifications, scheduling calendar holds, or enabling automatic email replies.The SDK aims to break down complex workflows into dependable “atomic commands” such as searching, checking out, or interacting with specific interface elements like dropdowns or popups. De

AI agents keep access to company data after their work is done IT teams responsible for identity security are concerned about AI agents’ ongoing access to company systems and the actions they take on users’ behalf, according to a Delinea’s 2026 Identity Security Report: The AI Enforcement Gap. “Written policy is only as good as your ability to enforce it at the moment an AI agent acts,” said Art Gilliland, CEO of Delinea. “Our research echoes what I hear f

AI is giving attackers a head start, Microsoft warns Threat actors are using AI to find bugs, build malware and run intrusions faster than defenders can keep up. Microsoft’s 2026 Digital Defense Report, covering July 2025 to June 2026, describes a near-term period in which attackers collect the benefits of AI first and defenders have to move quickly to close the gap. “AI is changing the physics of cybersecurity,” the company said. Bugs found faster than th

Apple tightens macOS disk access as AI agents become more powerful Apple plans to introduce additional controls for Full Disk Access in macOS, citing growing privacy risks as AI agents become more capable and autonomous. Users will need to take explicit action to grant apps this permission. The company has not specified a rollout date or detailed how the controls will work. Apple’s APIs include controls designed to protect users’ private data. Full Disk Ac

Reflection’s Beam trails top open models on coding tests but claims lower inference compute Reflection AI has built Beam, a 501-billion-parameter open-weight model for coding and agent tasks, and plans to publish the weights under an Apache 2.0 license later this month. Open-weight means developers can download the trained model and run it on their own hardware. Beam uses a mixture-of-experts design, so 23 billion of its parameters fire for any given token

Rogue OpenAI agents made unauthorized Wikipedia edits and millions of requests to Wikimedia Rogue OpenAI agents made unauthorized edits on Wikimedia wikis and sent millions of automated requests to Wikimedia’s public APIs, traffic that may have contributed to a partial outage of the Wikidata Query Service in May, the Wikimedia Foundation said on Monday. “The Wikimedia Foundation conducted its own investigation to see whether Wikimedia websites had been sim

PCI SSC calls for human approval of AI agent actions involving cardholder data The PCI Security Standards Council (PCI SSC) has published Security Considerations for AI Systems, guidance covering the protection of data supplied to AI systems in payment environments and defenses against AI-assisted attacks. Developed with industry stakeholders, the document addresses governance, deployment, access controls, testing and the application of PCI standards. Its

AI vulnerability patching has a grading problem Researchers at Northwestern University tested AI coding agents on 112 real security bugs. They found that a patch which stops a crash often fails the checks the project’s maintainers wrote for the fix. With Claude Opus 4.7, third of the patches that made the crash go away still failed those maintainer tests. If you’re thinking about letting an AI tool patch vulnerabilities for you, this is the number to look