Find published research by company, product, platform or technology.
Showing 21–40 of 131 dossiers
The May Antigravity agent ID is retired. Managed Agents now require the September preview ID and default to Gemini 3.8 Flash, alongside hooks, token budgets and scheduled sandboxes.
The incidents do not have a proven common attacker. Wiz's forensic evidence shows downstream abuse and resale of stolen keys, not that every platform breach caused the same misuse.
Stalwart 1.0.1 fixes local credential-file permissions and a tenant isolation bug, but changes Prometheus/OTLP metrics and leaves some migration WebUI cache pitfalls.
GitHub Apps can now authenticate Copilot SDK workloads without a user's credentials. Organisation admins control installation permissions, usage attribution and budgets.
MLflow CrewAI autologging silently logged API keys; 3.17.0 patches it, but previously exported traces and keys still need remediation.
The useful shift is architectural: agent permissions no longer have to depend only on the model or harness behaving correctly. OpenShell puts policy enforcement in the execution environment, while Sentry is designed to keep watching from a separate hardware trust domain.
Void SDK adds server routes and typed data access to Vite, Void CLI provisions Workers resources, and Void Platform provides a controlled multi-user deployment surface. The convenience comes with Cloudflare runtime dependencies and real deployment limits.
Muse packages persistent autonomous execution, credentials, payments, app access and memory into a mainstream consumer product. A September macOS hotfix now provides an early real-world lesson: agent containment has to protect not only the cloud runtime but also the local control path into the agent.
The useful change is where enforcement happens. Teams can now make unresolved leaked credentials a branch-policy failure, with organization and enterprise rollout plus API configuration for large repository fleets.
The corrected rollout matters for supply-chain configuration: teams can still remove PATs for qualifying GitHub Packages, but GitHub changed the precedence model after some npm update jobs were mistakenly routed through GitHub Packages.
The technical-preview feature separates Copilot CLI from GitHub Cloud for core coding, shell and repository workflows, giving regulated and isolated environments a supported agent path while leaving cloud-dependent capabilities such as GitHub-hosted model selection and web search unavailable.
Postmark’s new IP Allowlisting creates an extra sending boundary around API credentials: trusted infrastructure can send normally, while requests from outside configured ranges fail even if the token itself is valid. SMTP is not covered.
Railway Cloud Agents are managed, persistent development machines rather than a new model or harness. They reuse developers’ existing agent credentials, sleep when disconnected by default, retain disk state, and live inside Railway project environments—blurring the boundary between remote coding workspace and deployment platform.
GitHub OAuth apps can now use eight-hour access tokens with rotating refresh tokens, register up to 10 callback URLs, and explicitly control wildcard callback matching. New apps default to expiring tokens, while existing single-callback apps should review a legacy wildcard setting GitHub has now made visible.
Computer Use is now GA in both Gemini APIs, but it is an action-planning tool, not a hosted remote desktop: clients execute clicks and keystrokes and must handle safety decisions.
Mozilla reports more than seven times as many Firefox security fixes as a year earlier, while adopting weekly releases, confidential regression tests and a proposed strategy to avoid overlapping exploit-chain patch gaps.
Rashomon's experimental local recorder can expose discrepancies between a coding agent's closing claims and its tool execution. It is an observability aid, not a sandbox or tamper-proof security product.
The useful lesson is architectural rather than vendor-specific: coding agents inherit execution paths from ordinary developer tooling. If an agent shells out to Git without sanitising repository-local configuration, a hidden `.git/config` can become a host-level command channel that bypasses the controls users think govern the model.
The important shift is that agent orchestration itself becomes a managed API surface: context compaction, tool discovery, programmatic tool calls and subagent coordination can now come from OpenAI’s maintained Codex harness rather than an application team rebuilding those layers.
Self-Hosted Machines changes the architecture of Cursor’s Cloud Agents more than another model option would. Teams can keep code, build outputs, secrets and terminal/browser actions on infrastructure they control, but the planning/inference loop remains a Cursor service and enterprise teams become responsible for worker images, scaling, secrets and production validation.