Loading npm security reports…
8 AI design personas — v2.0 chunked execution with frontier planner + free/cheap chunk models, adversarial deliberation loops, opt-in community feedback, Kavi knowledge collection, DesignSpec producer path, wireframe skills, UX critique, Agent Skills for
LPM flags this version as an AI-agent control-surface risk. Installation automatically populates an AI-agent skill directory. If no compatible directory is detected, it targets Cursor by default.
Package defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgPackage source references dynamic require/import behavior.
dist/bin/cli.jsView on unpkg · L1Package source references weak cryptographic algorithms.
dist/lib/query-expander.jsView on unpkg · L1Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
dist/lib/install.jsView on unpkg · L1Package defines install-time lifecycle scripts.
package.jsonView on unpkg · L43Install-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkg · L43Package source references dynamic require/import behavior.
dist/bin/cli.jsView on unpkg · L1Package source references weak cryptographic algorithms.
dist/lib/query-expander.jsView on unpkg · L1Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
dist/lib/install.jsView on unpkg · L1