buildOne report1 publisher npm worms ran attacker code from committed Claude Code hooks
Worms spreading through npm in May and June 2026 committed a SessionStart hook to .claude/settings.json that runs a script when Claude Code opens the repo. Removing the package leaves that file in place, a dev.to write-up says.
Reality
- Evidence55
- Adoption
- Not scored
- Hype gap−10
- Incentives
- Not scored
- Confidence55
buildOne report1 publisher Copilot's --yolo removes the approval prompt but still obeys --deny-tool rules
Copilot's --yolo, /yolo and VS Code's Allow all remove only the approval prompt, according to a dev.to walkthrough of the Copilot docs. Deny rules still win, and the CLI and VS Code use separate permission systems that each need configuring.
Reality
- Evidence58
- Adoption
- Not scored
- Hype gap−5
- Incentives
- Not scored
- Confidence60
buildOne report1 publisher Copilot CLI pairs local Ollama models with a GA sandbox that excludes the CLI's own process
GitHub added local Ollama model discovery to Copilot CLI 1.0.94-0 and took its agent sandbox to general availability on October 7, dev.to reported. Keeping work on a developer's machine still takes manual steps, since Ollama must be installed first and offline mode is a separate setting.
Reality
- Evidence48
- Adoption
- Not scored
- Hype gap−5
- Incentives
- Not scored
- Confidence45
buildOne report1 publisher Classic dynpros and Smart Forms keep ABAP teams on Eclipse after VS Code ADT reaches GA
SAP's VS Code ABAP Development Tools are generally available, with 80% object-type parity against Eclipse ADT due by end-2026, a dev.to post says. The post's own list of gaps means most teams will keep Eclipse ADT running beside it.
Reality
- Evidence30
- Adoption
- Not scored
- Hype gap+30
- Incentives
- Not scored
- Confidence30
buildConfirmed2 publishers Microsoft plans to run MAI Code 1.1 Flash on developers' machines in GitHub Copilot, with a limited rollout starting by end-October 2026. Its figures come from one high-end laptop and local pricing is undisclosed, so teams cannot yet size the hardware or the bill.
Reality
- Evidence55
- Adoption12
- Hype gap+20
- Incentives55
- Confidence58
buildOne report1 publisher Theo Browne's AI-written tsc-rs type-checks VS Code 13x faster than tsc 6
Theo Browne's AI-written Rust port of the TypeScript compiler type-checks VS Code 13x faster than tsc 6 and cost over $420,000 in tokens. Browne says he never read the code, so the 181,711 ported tests it passes are the main evidence that it behaves correctly.
Reality
- Evidence45
- Adoption
- Not scored
- Hype gap+30
- Incentives35
- Confidence55
Anaconda has built tools from three acquired companies that run AI agent swarms and red-team them across more than 300 attack categories. Its controls for blocking risky agents look further along than its tools for auditing what they did.
Reality
- Evidence40
- Adoption25
- Hype gap+35
- Incentives80
- Confidence55
buildOne report1 publisher Warlock operators ran an EDR killer on at least 40 machines within two hours
Symantec says Warlock operators ran an AV/EDR killer across at least 40 machines in roughly two hours after a suspected SharePoint compromise. The ransomware payloads moved between domain controllers through SYSVOL replication.
Reality
- Evidence55
- Adoption
- Not scored
- Hype gap+20
- Incentives
- Not scored
- Confidence55
buildOne report1 publisher Claude Desktop needs OAuth or an mcp-remote bridge to use API-key MCP servers
Claude Desktop's custom connectors offer only OAuth sign-in for remote MCP servers, while five other clients take a static API key in a header. Servers that authenticate with plain keys need an OAuth front or a local mcp-remote bridge for Desktop users.
Reality
- Evidence55
- Adoption
- Not scored
- Hype gap+5
- Incentives30
- Confidence50
Warlock ransomware operators keep breaking in through unpatched SharePoint, Symantec reports
China-linked Warlock operators hit at least four organisations through SharePoint flaws in two months, Symantec says. Its report lists six 2026 SharePoint CVEs only as possible additions, and the entry it documents is still older flaws on servers never patched or mitigated.
Reality
- Evidence55
- Adoption
- Not scored
- Hype gap+15
- Incentives
- Not scored
- Confidence55
SleepyDuck operator re-lists fake Solidity extensions on Open VSX hours after a takedown
Pluto Security says the SleepyDuck operator re-listed fake Solidity extensions on Open VSX within hours of a takedown, in a stage it calls EtherDuck. Each wave stayed up about 19 hours, long enough for a single install to leave persistent access that the takedown did not remove.
Publishers:pluto.security
Reality
- Evidence55
- Adoption
- Not scored
- Hype gap+15
- Incentives60
- Confidence50
buildOne report1 publisher Microsoft publishes token and cache telemetry from 301,026 Copilot agent sessions
Microsoft released metadata from 301,026 GitHub Copilot agent sessions, covering 9.3 million LLM calls in one June week. Capacity planners now have real cache and token figures to test against, though the files measure resource use only and cannot show whether the output was any good.
Reality
- Evidence64
- Adoption
- Not scored
- Hype gap−5
- Incentives45
- Confidence60
buildOne report1 publisher TypeScript 7's Go compiler speedup scales with how much of your build is tsc
Microsoft's Go port of the TypeScript 7 compiler cut VS Code's full build from 125.7 to 10.6 seconds in its benchmarks. Tools that import TypeScript as a library may still need the TypeScript 6 API, so the upgrade belongs on a throwaway branch first.
Reality
- Evidence40
- Adoption
- Not scored
- Hype gap+15
- Incentives50
- Confidence45
buildOne report1 publisher One Codex prompt spawned 826 child agents on a model tier its user never authorized
One OpenAI Codex prompt spawned 826 child agents and burned about $78,000 in credits, according to the user's own reconstruction. Nearly all the counted tokens trace to an alpha client build, and only OpenAI's servers can turn them into dollars.
Reality
- Evidence35
- Adoption
- Not scored
- Hype gap+40
- Incentives
- Not scored
- Confidence30
buildConfirmed3 publishers The August 17 postmortem describes a sidecar that hit its concurrency limit while its autoscaler measured the host, then a VS Code retry bug that kept Copilot down hours after everything else returned.
Perspective Coverage
3 publishers
- Builder
- Builder 39%
- Operator
- Operator 38%
- Investor
- Investor 23%
Reality
- Evidence66
- Adoption82
- Hype gap−12
- Incentives58
- Confidence64
buildOne report1 publisher Attackers rode the Trivy compromise into Checkmarx's GitHub and out through its VS Code extensions
Mandiant's findings say the intrusion never reached Checkmarx One or production AWS, and that answers the vendor's question rather than the one a customer has about what a build box pulled in late March.
Publishers:checkmarx.com
Reality
- Evidence38
- Adoption
- Not scored
- Hype gap+25
- Incentives65
- Confidence45
buildOne report1 publisher Oizom builds a separate stack for every ticket so one developer can keep several tickets moving with one agent
Oizom's orchestrator gives each approved ticket its own branches, services and database copy, so one developer can run several AI agent tasks at once. Its team lead says the setup is mostly scripts, so the limit is how many live stacks one person can test.
Reality
- Evidence30
- Adoption8
- Hype gap+10
- Incentives30
- Confidence35
Microsoft's DebugMCP 1.1.4 left an unauthenticated debugger port open to malicious webpages
Imperva found Microsoft's DebugMCP 1.1.4 let a malicious webpage run code on a developer's machine through an unauthenticated port 3001 listener. The fix reached 1.2.0 with no advisory, so finding exposed machines means checking installed extension versions.
Reality
- Evidence58
- Adoption
- Not scored
- Hype gap+10
- Incentives40
- Confidence60
Four governments have put a bureau name on the fake-recruiter campaign against software developers, and their alert says the same crews also work as North Korea's remote IT hires, from the same IP addresses.
Perspective Coverage
8 publishers
- Builder
- Builder 34%
- Operator
- Operator 52%
- Investor
- Investor 14%
Reality
- Evidence70
- Adoption
- Not scored
- Hype gap+5
- Incentives40
- Confidence72
buildOne report1 publisher GitHub lost 3,800 internal repos to code running with its editor's permissions
A dev.to writeup traces roughly 3,800 exfiltrated GitHub repositories to one trojanised Nx Console install from the official Marketplace, where the sandbox that would have contained it has been an open feature request since 2018.
Reality
- Evidence42
- Adoption28
- Hype gap+18
- Incentives62
- Confidence45