cyberivy

Search results for “Coding Agents”

Full-text search across every article: title, summary, plain-language explanation, and the complete text — archived stories included. Typos are fine.

306 results for “Coding Agents”

  1. AutoJack: one web page is enough to hijack an AI agent

    #AI#Security#Microsoft

    … URL field or a prompt injection will do. Why it matters AI agents that browse the web on their own are increasingly being built into workflows in 2026. AutoJack demonstrates that such an agent can blur the line between …

  2. Hundreds of AI agents accelerate attack on 395 organizations

    #PaperCut#AI Security#AI Agents

    … A suspected Russian-speaking attacker used hundreds of AI agents to exploit two vulnerabilities in PaperCut NG/MF. GreyNoise documented at least 440 compromised instances belonging to 395 organizations in 48 countries on …

  3. Google Antigravity 2.0 Becomes an Agent Command Center

    #Google Antigravity#AI Coding#Developer Tools

    … Google Antigravity 2.0 is Google’s attempt to treat AI coding as more than autocomplete inside an editor. On May 19, 2026, Google introduced version 2.0 as a platform for working with agents: a desktop app, CLI and SDK …

  4. Microsoft Agent Governance Toolkit: guardrails for AI agents

    #Microsoft#Agent Governance Toolkit#AI Security

    … toolkit for runtime governance of autonomous AI agents. Microsoft describes the project as an MIT-licensed monorepo with packages for policy enforcement, identity, sandboxing and reliability engineering. The focus is not …

  5. WriteOut shows why AI sandboxes do not replace boundaries

    #Writer AI#WriteOut#AI Security

    … does The attack used a live preview feature for Writer agents. According to Sand Security, the preview ran under the same origin as the main application. That meant the victim's browser automatically attached the Writer …

  6. VoltAgent organizes agent building in TypeScript and a console

    #VoltAgent#VoltOps#AI Agents

    … engineering tool for developer teams that want to operate agents, not just experiment with them. The platform combines an open-source TypeScript framework with the VoltOps console, which the product page describes as …

  7. Strix tests apps with autonomous pentest agents

    #Strix#AI Security#AppSec

    … as another static warning feed, but as autonomous pentest agents that dynamically inspect applications, attempt to exploit possible weaknesses, and produce usable evidence. That puts Strix between a classic scanner, …

  8. Holo4 opens computer control to local AI agents

    #Holo4#H Company#Computer Use

    … runs for replay and download. Why it matters Computer-use agents are difficult to audit. A final score can show whether a task succeeded, but not reliably reveal which intermediate decisions were unsafe. Open weights and …

  9. qm gives teams separate workspaces for AI agents

    #qm#AI Agents#Team Collaboration

    … is not a new language model. qm organizes existing coding harnesses such as Codex, Claude Code, OpenCode or Pi as shared infrastructure. This is relevant for small companies that want to use agents with their own files, …

  10. Salt Code Puts Security Rules Inside Coding Assistants

    #Salt Code#AI Coding#AI Security

    … 1, 2026. The product is aimed at teams that already use AI coding assistants in daily work and no longer want to discover every security issue only in pull requests, SAST scans or production. The core idea: security …

Browse all AI news in the archive