Safeguard Blog · Oct 18, 2026 · 7:15 PM

VS Code 1.141.1 patches 10 CVEs, including a Copilot agent hook-edit bypass and an MCP sandbox escape

CVE-2026-102232 let prompt injection get the Copilot agent to edit a lifecycle-hook file without confirmation, and CVE-2026-102851 let one sandboxed MCP server use another server's approved network and write permissions; the rest are Workspace Trust bypasses and click-to-run RCEs. Update to 1.141.1 or later (check pinned dev containers too), then re-approve each MCP server's permissions, since the fix ignores old shared grants.

Read at safeguard.sh

GitHub Copilot

AI coding assistance across editors, GitHub, and the CLI

More news

View all

Google AI Studio can now push vibe-coded Android apps to a private Play Store library, no developer account

Rolling out in the US and select markets to users 18+, apps built in AI Studio go straight to a Personal Library in the Play Store with no APK sideloading, $25 fee, or Google review, and sharing with a small group of friends and family is planned. Going public will mean onboarding to a developer profile and normal Play review, an option Google says arrives in the coming months (Google Play blog)…

Ars Technica 25 minutes ago

MIKE, an open-source kanban harness, runs local-LLM coding agents inside gVisor sandboxes

Each card on MIKE's web kanban board is a task: pressing start runs an agent in a gVisor sandbox on its own Git worktree with a read only repo mount, retries failed tool calls, and parks stuck work in review for you. The author built it entirely with llama.cpp hosted local models and added client side rate limits, an offline friendly UI, and a bearer token REST API for starting tasks from scripts (Show HN)…

GitHub (SoftwareRenderer/MIKE) 1 hour ago

Junie CLI and ZCode could run code from MCP servers declared in a cloned repo; only Junie is patched

CVE 2026 111091 (JetBrains Junie CLI, fixed in 26.8.3) and CVE 2026 88755 (Z.ai's ZCode, no known fix, public PoC) both let opening a crafted repository auto start its workspace MCP servers, which over stdio are just commands, scored 7.8 High. Update Junie, avoid opening untrusted repos or PR branches in ZCode, and treat repo local MCP and hook configs as code…

Threat Frontier 3 hours ago

Safeguard makes MCP tool calls unlimited on every plan, including Free

As of Oct 18, agents connected to the supply chain security platform from Claude, ChatGPT, Cursor, or custom setups can run package, CVE reachability, and dependency checks with no monthly cap, per minute limit, or per call charge. Its API also moves to pay as you go, with 10,000 deterministic calls a month included and $0.10 per 1,000 after that…

Safeguard Newsroom 4 hours ago

OpenAI team used Codex and GPT-6 Astra to merge 1,400+ cleanup PRs and delete 800k lines of dead code

OpenAI's Core Experimentation team gave Astra a vague one line Codex prompt to find dead code, and it checked past PRs, Slack, Statsig, and production profiling before proposing each deletion; five engineers merged the results part time over two weeks, shrinking one container image from 3.31 GB to 1.72 GB. The team says GPT 6.1 Sol found 92% of Astra's issues at about 14% of the API cost, though some proposals added more complexity than they were worth…

OpenAI Developers Blog 6 hours ago

Spotted something we missed? Start a thread.