npm AI-agent policy reports, with evidence.

This package has a concrete automatic postinstall chain that modifies and deletes files in a user's Claude Code configuration. The global-install trigger does not require a separate expli...

The postinstall hook mutates a foreign global agent control surface and installs an auto-starting background plugin. This is concrete unconsented install-hook abuse, even though no instal...

This is an unconsented postinstall mutation of a broad AI-agent control surface. The automatic hook, skill, statusline, and global instruction changes meet the install-hook abuse blocking...

The automatic postinstall hook mutates a foreign AI OAuth control surface, satisfying the install-control-surface block boundary. The hook is source-confirmed and does not require a user...

The automatic lifecycle hook broadly mutates foreign AI-agent skill registries. This meets the install-control-surface blocking policy regardless of the absence of direct JavaScript exfil...

The package combines an automatic lifecycle-installed server with automatic broad workspace agent-skill writes and embedded agent-directing instructions. This creates a concrete persisten...

The package has a concrete automatic postinstall path that persists instructions into Claude Code rather than requiring an explicit setup command. This meets the install-time AI-agent con...

The automatic lifecycle hook modifies global Claude telemetry to capture sensitive agent-session content and directs it to a remote endpoint. Its additional hook and permission merger exp...

The inspected lifecycle path establishes automatic, non-interactive mutation of a consumer project's Claude hook settings. Under the install-control-surface policy, that concrete postinst...

The lifecycle hook performs broad, destructive AI-agent configuration mutation in the consumer project without an explicit user command. This meets the install-hook abuse blocking policy.

The automatic postinstall hook persistently injects behavior-bearing instructions into multiple unrelated AI-agent configurations. This is unconsented install-time AI-agent control-surfac...

The package performs automatic postinstall rewrites of user Cursor and Codex MCP settings, alongside broad consumer-project mutation. This meets the blocking policy for unconsented lifecy...

The postinstall hook automatically writes package content into global Claude and Codex agent directories. This concrete, broad agent-control-surface mutation meets the install-time blocki...

This is an unconsented postinstall mutation of broad foreign AI-agent control surfaces, combined with automatic remote native-code execution. It meets the install-hook abuse blocking policy.

This is a concrete remote AI-agent control channel: a default startup connection accepts server-directed skill replacement from arbitrary URLs. The absence of lifecycle hooks does not mit...

This is an unconsented install-time mutation of a broad AI-agent control surface. The automatic postinstall, disabled consent path, persistent global skill, hooks, and instruction changes...

The lifecycle hook performs broad, persistent Claude Code control-surface changes without user consent. This meets the install-hook abuse blocking policy even though the inspected path do...

This is an unconsented postinstall mutation of a foreign AI-agent control surface, with persistent automatic command execution. The existence checks limit targets but do not remove the in...

This is an unconsented postinstall mutation of foreign AI-agent control surfaces, combined with remote executable delivery and privileged host configuration changes. The global-install gu...

The package has a concrete automatic postinstall path that modifies broad consumer AI-agent configuration and instruction files. This meets the install-hook abuse blocking policy even wit...

The postinstall path unconditionally configures global Claude telemetry that captures AI-session content and directs it externally. This meets the install-time AI-agent control-surface ab...