npm security reports, with evidence.

The package has a concrete automatic postinstall chain that modifies foreign AI-agent configuration and enables a plugin. This meets the install-hook abuse boundary despite no observed se...

The automatic lifecycle hook broadly mutates consumer and machine-level AI-agent configuration, including an executable pre-tool hook. This meets the install-control-surface blocking poli...

The package automatically modifies a foreign user-wide AI-agent configuration and enables remote collection of sensitive Claude interaction content. This concrete install-time control-sur...

This is an automatic postinstall mutation of broad, foreign Claude and Codex command control surfaces, with persistence and automatic updating. The global-install guard does not provide s...

The package combines an automatic global postinstall hook with broad third-party MCP configuration writes and a remote, unpinned executable delivery path. The global-only guard and opt-ou...

The package performs broad, automatic mutation of a consuming project and persists control over its entry files through an injected build plugin. Reviewer-directed prompt-injection langua...

The lifecycle hook automatically replaces a foreign AI-agent executable with opaque bundled binaries. Backups and hash checks do not remove the install-time control-surface takeover.

The postinstall hook automatically installs command hooks into the user's Copilot configuration and persists shell-profile code. This is a concrete unconsented mutation of foreign AI-agen...

The package performs an unconsented postinstall write to a generic consumer-project AGENTS control surface and injects AI-agent instructions. This meets the install-control-surface blocki...

The package performs unconsented privileged-capable system mutation from an automatic install hook and repeats it on ordinary execution. This is a concrete install-hook abuse path, not me...

This is an unconsented install-time mutation of broad consumer project and AI-agent control surfaces, with durable execution paths added to later installs and Git operations. The behavior...

The automatic postinstall hook writes package-controlled content into the global Claude Code skills directory. That concrete lifecycle-based agent control-surface mutation meets the publi...

The automatic lifecycle hook performs remote content retrieval and broad global AI-agent configuration writes. That is concrete unconsented install-time control-surface mutation.

This is concrete unconsented postinstall mutation of a broad AI-agent control surface. The lifecycle hook persists package-controlled commands and instructions globally, meeting the insta...

The package performs unconsented postinstall mutation of the user's Claude command area and automatic MCP registration. Those actions constitute a concrete install-time AI-agent control-s...

This is an unconsented postinstall mutation of broad project and AI-agent control surfaces, reinforced by detached lifecycle reconciliation. No secret theft was found, but the automatic c...

Source directly shows a site token copied into Authorization headers and reused for requests to numerous alternate domains. This is concrete credential exfiltration rather than ordinary p...

This is an automatic install-time path that invokes opaque native code to configure Codex and Claude hooks, rather than an explicit user setup action. The visible source establishes a bro...

The hidden phrase-based privilege elevation, unauthenticated proxy route, and unrestricted command runner form a concrete remote agent-control chain. The lack of an install hook does not...

The package performs automatic postinstall mutation of both Codex and Claude global skill directories and installs Python dependencies into the user environment. This meets the install-co...

This is a complete automatic lifecycle and self-dependency chain that broadly mutates a foreign AI-agent control surface. The OAuth implementation does not neutralize the unconsented pers...