npm AI-agent policy reports, with evidence.

The automatic lifecycle chain performs concrete writes to foreign AI-agent skill directories. The bundled implementation is also obfuscated, reducing auditability of this install-time beh...

The automatic postinstall chain reaches code that writes to the .agents AI-agent control surface. This is concrete install-hook abuse under the stated policy, despite the write being scop...

The automatic lifecycle hook performs broad, unconsented mutation of foreign AI-agent directories. This meets the install-control-surface policy for blocking publication.

The postinstall hook writes this package's skill files into Claude Code's project .claude/skills directory without an opt-in command. That is unconsented install-time mutation of a foreig...

The automatic lifecycle hook modifies a foreign, broad AI-agent control surface, and its default-empty response authorizes the write. This is concrete install-hook-based AI-agent control...

Postinstall automatically mutates project and user-home agent control files for Hermes, OpenClaw, OpenCode, and Cursor, including enabling a Hermes plugin. That is unconsented foreign con...

Postinstall unconditionally deploys Cursor hooks, rules, skills, and commands into the consumer project, which is an unconsented mutation of a foreign agent control surface. Optional MCP...

The install lifecycle unconditionally invokes an installer whose stated effect is writing skills into multiple third-party agent hosts. That is unconsented postinstall mutation of a broad...

The automatic postinstall hook silently replaces consumer-project Claude Code skills, which is concrete install-hook abuse under the supplied policy. The behavior warrants blocking even t...

The postinstall hook mutates project and user-home AI agent control files for OpenCode, Cursor, Hermes, and OpenClaw without a separate user command. That is unconsented install-time cont...

The postinstall hook automatically runs a broad plugin install into Claude, Codex, and Cursor user configuration during a global package install. That is unconsented lifecycle mutation of...

A global npm postinstall automatically installs this package's plugin into Claude, Codex, and Cursor and rewrites the user Codex config, which is an unconsented broad agent control-surfac...

Unconsented postinstall mutation of user-global ~/.claude/settings.json enables prompt and tool-content export to a package-controlled collector. That is an active agent-control hijack, n...

Global postinstall unconditionally mutates foreign, broad agent control surfaces, including Cursor, Claude, and Codex config, command, and skill files. That is unconsented install-time ag...

Postinstall unconditionally mutates the user-wide Claude Code control surface and enables prompt and tool telemetry to a package-controlled collector. That is unconsented install-time age...

The postinstall path is an automatic global-install write into Claude Code's broad settings and hook surface, including tool-use interceptors and a third-party plugin pin. Opt-out flags a...

The postinstall hook unconditionally replaces directories in the consumer project's .claude/skills with a package-supplied Claude skill that auto-triggers on generic UI requests. That is...

The automatic postinstall performs unconsented, overwrite-enabled mutation of broad AI-agent control surfaces. This is concrete install-hook abuse under the stated policy.

This is concrete, unconsented postinstall mutation of foreign and machine-level AI-agent control surfaces. The lifecycle hook abuse warrants blocking even without demonstrated credential...

The automatic postinstall modifies a foreign, user-level Claude Code configuration and enables export-oriented telemetry for prompts, responses, and tool details. This is concrete install...

This is an unconsented automatic install-time mutation of foreign AI-agent control surfaces. The opt-out and name check do not change that the deletion is triggered by installation.