Coding Tools
CodeQL 2.26.0 Enhances Security with AI Detection
GitHub Changeloghigh confidence
Why it matters
- →CodeQL 2.26.0 enhances security by detecting AI prompt injection vulnerabilities.
- →The update supports Kotlin 2.4.0, expanding its language coverage.
- →Improved accuracy in security queries reduces false positives, aiding developers.
GitHub has released CodeQL 2.26.0, enhancing its static analysis capabilities with new features and improved accuracy. This update includes support for Kotlin 2.4.0 and introduces a query to detect AI prompt injection vulnerabilities in JavaScript and TypeScript. Additionally, it refines security queries across various languages, such as C#, Go, and Python, to reduce false positives and enhance detection. These improvements aim to bolster security for developers using GitHub code scanning, particularly in AI-related applications.
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.
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.