npm detections from LPM Firewall.

The package performs unconsented postinstall mutation of both consumer project and AI-agent control surfaces, including third-party Claude plugins and user-wide Codex registrations. This...

The package performs unconsented privileged host mutation during installation and repeats it at CLI startup. This is concrete install-hook abuse even though inspected files did not show s...

This package creates an automatic install-time remote code execution path from mutable external content and launches native installers. The behavior is concrete and runs with the installi...

The automatic lifecycle chain mutates a foreign AI host and installs a detached self-healing mechanism. This is concrete install-hook abuse even though no credential theft was found.

The package automatically modifies consumer lifecycle configuration and installs AI-agent plugins during postinstall. This is concrete install-hook abuse rather than an explicit user-invo...

Although installation has no automatic registry lifecycle hook, the package combines deliberate obfuscation with remote-controlled shell execution in its normal runtime path. This is a co...

The package embeds a delayed, geographically and language-targeted browser-disruption payload in its entry bundle. The absence of lifecycle hooks does not mitigate this concrete runtime a...

This is concrete credential exfiltration to a package-controlled hard-coded server combined with automatic command interception and persistence. The guarded global-install condition does...

The package combines an automatic install hook, non-interactive consumer-project mutation, and unrequested installation of third-party AI-agent plugins. This is a concrete unconsented lif...

The package has a postinstall hook that automatically changes both Codex and Claude skill directories and installs user-environment dependencies. This is concrete install-hook abuse under...

The hidden subscription and outbound-email functionality is unrelated to a cloud-storage explorer and processes user contact data. Its restricted development trigger reduces exposure but...

The built runtime automatically forwards a Cloudflare API credential to a package-vendor host and mixes unrelated hard-coded t3cloud URLs into its cache purge flow. This is concrete crede...

This package performs unconsented install-time mutation of broad Claude and Codex control surfaces, persists itself, and configures automatic credential synchronization to a hard-coded re...

The package automatically persists a user-scope AI-agent command rather than requiring an explicit setup action. Its npx latest registration makes the installed control surface execute a...

The automatic lifecycle path rewrites foreign DSH authentication and sandbox safeguards, while the launcher persists an unsafe default in user configuration. This is concrete install-hook...

The package performs unconsented postinstall mutation of a foreign, broad AI-agent skill directory. Its automatic remote archive download and extraction increases the install-time supply-...

The automatic lifecycle hook modifies foreign global AI-agent configuration surfaces and performs further user-environment dependency installation. This meets the install-control-surface...

This is an unconsented postinstall mutation of a foreign AI-agent control surface that weakens both sandboxing and authentication. The lack of observed exfiltration does not neutralize th...

The automatic postinstall fan-out mutates broad third-party AI-agent control surfaces, meeting the install-control-surface blocking policy. No exfiltration was found, but it is not needed...

The automatic lifecycle hook rewrites third-party AI-agent security controls, including authentication and sandbox behavior. This is concrete install-hook abuse with a persistent capabili...

The package uses an automatic install lifecycle to mutate foreign, broad AI-agent control surfaces and inject persistent agent instructions. This is concrete install-hook abuse under the...