Coding Tools
GitHub launches package firewall for npm
GitHub Changeloghigh confidence
Why it matters
- →Protects automated CI/CD runners and AI agents from malicious dependencies at install time.
- →Adds a proactive policy layer for npm packages beyond standard vulnerability scanning.
- →Addresses the specific risk of supply-chain attacks in headless, unmonitored build environments.
GitHub has released its package firewall in public preview for GitHub Enterprise Cloud customers, targeting the growing threat of malware injected during package installation. The service functions as an intermediary between endpoints and upstream registries, inspecting npm packages for malicious activity before they are downloaded. Administrators can configure policies to check against the GitHub Advisory Database and detect supply-chain risks such as attestation downgrades. While currently limited to npm and free during the preview period, the tool aims to secure automated environments like CI/CD pipelines and AI coding agents from dependency-based attacks.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1New Worm Targets AI Infrastructure in Supply Chain
WIRED AI · July 21, 2026 · Background
- 2npm Introduces Publish-Time Malware Scanning
GitHub Changelog · July 28, 2026 · Related
- 3
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.