PrivSec Lab wrote
Jul 6, 2026 in ai-coding - Databricks open-sourced Omnigent, a meta-harness that orchestrates AI coding agents like Claude Code, Codex and Cursor. What a meta-harness is, its three capabilities, and where it fits for developers.
Read more…PrivSec Lab wrote
Jul 6, 2026 in ai-coding - Researchers showed that malicious AI agent skills can hide from static scanners using a technique called SkillCloak, and real malicious skills have appeared on agent marketplaces. What skills are, how the evasion works, and how to stay safe.
Read more…PrivSec Lab wrote
Jul 5, 2026 in ai-coding - Sysdig documented JadePuffer, which it calls the first agentic ransomware - an AI agent that ran an entire extortion attack on its own, from break-in to encryption. What it did, why 'agentic' matters, and how to defend.
Read more…PrivSec Lab wrote
Jul 4, 2026 in ai-coding - Mistral released Leanstral 1.5, a free Apache-2.0 model for Lean 4 that formally proves math and code correct. What formal verification is, the benchmark numbers Mistral claims, and where the model actually fits for developers.
Read more…PrivSec Lab wrote
Jul 4, 2026 in ai-coding - A leaked video revealed Project Aion, an internal Microsoft prototype where Copilot replaces the Windows shell (no Start menu, taskbar or desktop). It runs on a web-based codebase called Win3 inside Edge. The video is reportedly about two years old, so the project is very likely abandoned, and Microsoft has not commented.
Read more…PrivSec Lab wrote
Jul 3, 2026 in ai-coding - Cato AI Labs disclosed two critical Cursor flaws nicknamed DuneSlide (CVE-2026-50548 and CVE-2026-50549, CVSS 9.8). They allow zero-click remote code execution via indirect prompt injection. Here is how they work and why they are already fixed in Cursor 3.0.
Read more…PrivSec Lab wrote
Jul 3, 2026 in ai-coding - Anthropic has brought Claude Fable 5 back with new cybersecurity safeguards and shared a jailbreak severity framework. Here is what came back, the safety classifiers, the four severity criteria, and what Anthropic has promised.
Read more…PrivSec Lab wrote
Jul 2, 2026 in ai-coding - Z.ai has launched ZCode, a free agentic coding tool powered by GLM-5.2 that undercuts Cursor and Claude Code on price. Here is what ZCode is, who it is for, how it compares, and how the GLM Coding Plan pricing works.
Read more…PrivSec Lab wrote
Jul 2, 2026 in ai-coding - Kimi K2.7 Code is now generally available in GitHub Copilot, and it is the first open-weight model you can pick in the Copilot model picker. Here is who gets it, why the open-weight, lower-cost angle matters, and how billing and enablement work.
Read more…PrivSec Lab wrote
Jun 30, 2026 in ai-coding - Claude Sonnet 5, Anthropic's newest Sonnet-class model, is now generally available in GitHub Copilot. Here is who gets it, what it is good at for everyday and agentic coding, and how it fits alongside the other Claude options.
Read more…Browser security
What your browser exposes, and which countermeasures actually work.
Read the research →Network privacy
Where your traffic leaks, and how to verify it yourself.
Read the research →Tooling
Independent benchmarks - no sponsorships, no marketing fluff.
Read the research →