npm AI-agent policy reports, with evidence.

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 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...

The source establishes an automatic postinstall chain that broadly alters foreign AI-agent configuration and extension directories. This meets the install-control-surface blocking policy...

The package's automatic postinstall writes and configures broad consumer AI-agent and Git control surfaces, including a hook that can block agent completion. This meets the install-time A...

The package performs unconsented install-time remote code execution and mutates a foreign AI-tool installation outside its own package directory. The interactive coding-agent wizard is gu...

This is concrete unconsented postinstall mutation of multiple foreign AI-agent control surfaces, including a remote latest npx MCP command. The guard against global installs does not limi...

The package automatically persists itself into Claude Desktop through a postinstall hook, which meets the install-control-surface blocking policy. The resulting MCP process reads a local...

The automatic lifecycle hook combines unauthenticated remote content retrieval with writes to broad, foreign AI-agent instruction directories. This is concrete unconsented agent control-s...

The automatic lifecycle hook performs broad consumer-project agent and Git control-surface mutation. Its resolution guard does not establish user consent for those changes.

This is an unconsented postinstall mutation of a consumer project's broad AI-agent control surface. Guards limiting the target project do not remove the automatic hook and skill injection.

The automatic lifecycle hook retrieves remote content and places agent instructions into several foreign global control directories. This satisfies the install-time AI-agent control-surfa...

This is concrete unconsented postinstall mutation of a consumer AI-agent control surface, combined with remote thin-mode code/content deployment. The preservation of an existing configura...

The package performs a concrete, automatic postinstall write to a user-wide agent extension location and the installed code modifies agent control inputs. This meets the install-control-s...

The automatic postinstall hook writes a foreign Claude Desktop MCP configuration and registers this package as a tool without a user command. That meets the install-control-surface blocki...

This is an unconsented postinstall mutation of a foreign, broad AI-agent control surface. The conditional binary check does not make the automatic global hook installation safe.

The package performs automatic, persistent, broad AI-agent and consumer-project mutations from postinstall. This meets the blocking policy for unconsented lifecycle mutation of a foreign...

The package has a concrete automatic postinstall chain that modifies multiple foreign AI-agent configurations and installs an enabled host hook. This meets the install-control-surface blo...

The package has a concrete automatic install-time path that weakens a foreign agent's permission and authentication controls. No exfiltration was needed to establish this install-hook abuse.

This package has a concrete, unconsented postinstall path that modifies multiple foreign AI-agent instruction surfaces. The absence of network or shell behavior does not remove the contro...