Loading npm security reports…
Evaluation framework for LLM knowledge inputs — prompts, RAG corpora, skills, agent workflows. Fix the model, vary the artifact. Built-in statistical rigor: bootstrap CI, Krippendorff α, length-debias, saturation curves.
Static analysis completed at 93.0% confidence. No malicious behavior was detected; 11 low-signal pattern(s) were surfaced and cleared.
Package source references dynamic require/import behavior.
dist/grading/assertions.jsView on unpkg · L375This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/renderer/observation-inbox-renderer.jsView on unpkgPackage source references dynamic require/import behavior.
dist/grading/assertions.jsView on unpkg · L375This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/renderer/observation-inbox-renderer.jsView on unpkg