Plugin4Shell: Copilot fix confirmed and Anthropic assigns CVE to agent plugin flaw
Microsoft's VS Code 1.136.0 fix supersedes the original Copilot-unpatched status; Anthropic has assigned CVE-2026-86063.
Find published research by company, product, platform or technology.
Showing 61–80 of 442 dossiers
Microsoft's VS Code 1.136.0 fix supersedes the original Copilot-unpatched status; Anthropic has assigned CVE-2026-86063.
Pi’s first stable release is interesting less for another coding-agent version number than for what its deliberately minimal core now considers mature enough to include: MCP, code-driven tool orchestration and model routing.
The post-release evidence sharpens the original story. Qwen3.8-27B can retain useful agentic-coding performance at practical 4-bit sizes, but local model quality is not a property of the checkpoint alone: quantization, reasoning effort, context handling and the agent harness can materially change the result.
Android Studio’s agent layer has crossed an important boundary from preview features into the stable channel: domain-specific skills are preloaded and auto-selected, while Gemma 4 can execute tool-calling code tasks locally without sending source code to a cloud model.
OpenAI’s internal data turns “agents make researchers faster” into a measurable operating model: heavy concurrent agent use, record experiment throughput and rising task complexity, alongside high token spend and persistent human intervention on longer work.
The useful part of Smaug Agentic is not another frontier-style benchmark claim. Abacus.AI is publishing a drop-in Kimi K3 derivative that targets a specific production failure mode in coding agents: long runs that burn the reasoning budget without converging. The weights and model card are public, but the training data is not disclosed and the benchmark gains remain vendor-produced.
A new buyer survey connects the shift from SaaS seats to agent usage with real budget anxiety: 46% report higher-than-expected agent costs and 45% say oversight eats more than a quarter of expected productivity gains. Preferences are not purchasing outcomes.
Builders can automate Stripe revenue and reconciliation analysis, but must plan for API permissions, asynchronous jobs, result retention and a February 2027 query-billing transition.
The useful shift is not another CLI convenience. A coding agent can now create a Shopify dev environment, populate it with existing API and bulk-operation tooling, test against it and tear it down without a person opening the Dev Dashboard.
PHPUnit 13.4.7 corrects skipped-class exit and stop semantics that could mislead CI or agent runners even when output reports skipped tests.
The useful part is not the 800,000-line headline. GitHub has published unusually detailed receipts for a production-scale agent-assisted migration: roughly $120,000 of token spend, 14.5 weeks of incremental releases, dozens of regressions, extensive compatibility tests and a workload-specific jump from 7.55 to 120 session lifecycles per second.
gh-aw v1.2.3 pre-release adds breaking security/default routing changes, connector migration, mandatory checksum pins, protected-file merge gates and MCP write opt-in.
Google has turned its Ads API helper into a reusable agent plugin rather than a standalone project. For developers maintaining ad-tech integrations, the material change is that agent workflows can now ground themselves in current Protobuf schemas and execute validated reporting against real Google Ads accounts instead of relying only on model memory.
OpenShell v0.1.8 hardens agent egress and filesystem policies, changes credential and OCSF audit schemas, and fixes gateway leaks. Existing integrations may need migration.
The useful change is containment rather than another browser-agent feature. Teams can let an agent operate a real browser while constraining its HTTP and HTTPS reach to the site and dependencies the task actually needs, reducing the blast radius of prompt injection, bad tool decisions or untrusted page content.
TanStack AI core has moved beyond its 1.0 GA: 1.4 adds MCP request metadata, 1.3 distinguishes loop limits from normal completions and earlier updates improve cancellations and runtime reliability.
Devin Fusion's persistent lead/sidekick architecture now has newer model choices and independently reported cost/quality comparisons, changing its practical deployment economics.
Project Rubicon uses object storage, disposable replicas and a reference transaction service to accommodate agent-driven parallel Git writes; access remains limited.
WebMCP tools can now emit PostHog's standard `$mcp_tool_call` event through posthog-js. The implementation adds privacy redaction and omits arguments/results, but only works for sites that enable the feature and initialise instrumentation before registering tools.
Cloudflare Computer 0.7 makes agent code resumable and interruptible. The important catch: recovery replays code, and unrecorded external actions can be repeated even if they already succeeded.