npm detections from LPM Firewall.

This is an unconsented postinstall mutation of broad consumer AI-agent configuration and instructions. The explicit hook command does not remove the automatic MCP and guidance changes.

The package has a concrete automatic postinstall chain that modifies multiple AI-agent homes and installs hooks, rather than requiring an explicit setup command. This meets the install-co...

The automatic postinstall hook establishes privileged, hidden persistence and installs extra software on Windows. These actions are concrete install-hook abuse regardless of the package's...

The package performs unconsented postinstall mutation of consumer AI-agent control surfaces and deliberately removes its own npm traces. That meets the install-control-surface blocking po...

This is an automatic postinstall mutation of a broad AI-agent control surface, not an explicit user-command setup. The recurring hooks and global instruction writes establish concrete per...

The lifecycle hook creates privileged persistence and installs software automatically, establishing a concrete install-hook abuse path. The source also contains an explicit scanner-avoida...

This is concrete data exfiltration from AI-agent session stores, coupled to automatic MCP-server startup collection and optional persistence. The absence of an install hook reduces instal...

The source directly collects GitHub credentials and sends them to an external service as bearer authentication. The lack of an install hook limits the trigger but does not remove the cred...

The automatic lifecycle chain modifies consumer AI-agent configuration and adds a hook that can block agent session termination. This meets the install-hook abuse blocking policy.

This is a concrete unconsented postinstall mutation of global Claude Code configuration and instructions. The package's registry update check does not mitigate the lifecycle control-surfa...

This is concrete install-hook abuse: an automatic lifecycle hook establishes elevated persistence and makes unrelated system and project changes. The behavior is not limited to explicit u...

This is concrete install-hook abuse: an automatic lifecycle script establishes elevated persistence and installs system dependencies. The localhost-only check does not offset the unconsen...

The package automatically persists package-controlled instructions into multiple unrelated AI-agent skill directories during installation and runtime. The opt-out does not make this an ex...

The automatic lifecycle chain is complete: postinstall invokes connect, which registers MCP integrations at user or global scope. This meets the install-time foreign AI-agent control-surf...

This is an unconsented postinstall mutation of broad AI-agent control surfaces. The forced global installation makes the behavior concrete and block-worthy.

The automatic postinstall mutation of ~/.claude installs package-controlled agent instructions and a command into a pre-existing AI-agent environment without explicit consent. This meets...

The postinstall hook performs an unconsented global installation of a foreign AI-agent package when local checks fail. This concrete install-time control-surface mutation meets the publis...

The package performs automatic privileged persistence and dependency installation from a postinstall hook. These actions are concrete install-hook abuse regardless of the watchdog's state...

The package performs unconsented postinstall mutation of global Claude settings that enables detailed telemetry export. This meets the install-hook abuse blocking policy.

This is an unconsented postinstall mutation of a broad AI-agent control surface that enables export of sensitive interaction content to a remote endpoint. The behavior is concrete and aut...

The automatic postinstall hook mutates a foreign project AI-agent control surface and deletes existing directories. This is concrete unconsented install-hook abuse despite the absence of...