npm detections from LPM Firewall.

The package directly harvests a local GitHub token and transmits it to a non-GitHub endpoint. The absence of an install hook limits activation to CLI use but does not remove the credentia...

The automatic postinstall-to-initializer chain and obfuscated payload establish install-hook abuse. The initialization targets multiple foreign AI-agent configurations, meeting the blocki...

This is an automatic postinstall mutation of foreign AI-agent control surfaces, coupled with instructions to route sensitive wallet and password actions through the package. The behavior...

This package has no npm lifecycle hook, but its explicit global setup persistently modifies broad AI-agent control surfaces, uploads conversation content, and remotely updates the execute...

This is an unconsented postinstall mutation of broad AI-agent control surfaces, including automatic command-hook registration. The absence of observed network exfiltration does not remove...

Source establishes an explicit-command persistence chain from broad AI-agent hooks to authenticated uploads at a hard-coded HTTP IP endpoint. The lack of an install lifecycle hook reduces...

The automatic postinstall invokes an opaque native installer that mutates third-party AI-agent hooks and settings. This is a concrete unconsented install-time control-surface modification.

This is an unconsented postinstall mutation of a broad, foreign AI-agent control surface that enables export of sensitive Claude interaction content. The automatic trigger and persistent...

This is an unconsented postinstall mutation of a consumer project's broad AI-agent control surface. Guardrails against collisions and transitive instances do not establish user consent fo...

This is an unconsented install-time mutation of both consumer project files and AI-agent control surfaces, including automatic plugin installation and user-wide Codex changes. The behavio...

The automatic postinstall execution of an unverified native binary to install and modify Codex and Claude Code hooks is a concrete install-time AI-agent control-surface mutation. This mee...

The package performs an automatic postinstall installation of native code that mutates third-party AI-agent hook and configuration surfaces. This is concrete unconsented install-hook abus...

This is concrete screenshot data exfiltration to a built-in third-party endpoint, not merely a local screenshot-review tool. The absence of an install hook reduces propagation risk but do...

This package has an automatic install-time host-mutation chain with privileged system-package installation and destructive rebuild preparation. The absence of confirmed exfiltration does...

The source implements the policy-defined malicious chain: an automatic install lifecycle broadly mutates AI-agent controls and installs/configures a separate executable MCP dependency. Th...

The package has a concrete automatic install-time chain that deletes and replaces dependencies of a foreign coding agent. Fixed versions and disabled scripts reduce payload risk but do no...

This is concrete install-hook abuse and credential exfiltration, not merely a user-invoked account-management tool: the global lifecycle hook changes broad AI CLI control surfaces and the...

The automatic postinstall mutates a foreign, user-wide AI-agent configuration and registers an opaque executable for later execution. This meets the install-control-surface blocking polic...

This is an unconsented postinstall mutation of the user's Cursor MCP control surface, combined with automatic skill deployment and remote binary retrieval. Integrity checks on the downloa...

The package has a registry install lifecycle hook that automatically fetches and writes agent instructions across unrelated global tool directories. That concrete control-surface mutation...

The package combines an automatic lifecycle mutation with remote-directed installation of another release of itself. This is a concrete install-hook self-dependency chain with persistent...