npm AI-agent policy reports, with evidence.

The automatic lifecycle hook mutates foreign, broad AI-agent configuration surfaces without consent. This meets the policy threshold for blocking install-hook-based AI-agent control hijac...

The postinstall hook unconditionally mutates Claude Code and Codex global MCP configuration to launch this package's server, which is an unconsented install-time write to foreign agent co...

The postinstall hook mutates Muse's global user skill catalog with --force and no prompt, so the bundled skill auto-loads in later Muse sessions. That is an unconsented install-time write...

This is a concrete unconsented postinstall mutation of a foreign, user-wide AI-agent control surface. The conditional Muse check does not provide user consent.

The postinstall hook silently registers this package as an MCP server in both Claude Code and Codex home configs. That is unconsented install-time mutation of foreign agent control surfaces.

The package performs automatic postinstall mutation of broad, foreign AI-agent configuration surfaces. That behavior meets the install-control-surface blocking rule regardless of whether...

The automatic lifecycle hook modifies foreign consumer configuration and routes an AI SDK through the package’s bridge. The associated code collects and transmits AI-agent telemetry, esta...

The automatic lifecycle hook writes instructions into several foreign AI-agent configuration trees. This concrete unconsented control-surface mutation meets the blocking policy.

Automatic postinstall mutates a broad, foreign AI-agent control surface, including machine-home Hermes and OpenClaw paths and Cursor hook reload, without a consent gate. That is install-t...

The postinstall hook silently mutates Claude Code's project skill directory, a foreign agent control surface, and the written files are instructions the agent will follow. That install-ti...

The postinstall hook mutates the foreign Codex config at ~/.codex/config.toml by default, enabling hooks and a publisher MCP endpoint with no consent prompt. Opt-out environment variables...

The package uses an automatic lifecycle hook to alter a user's global AI-agent instructions and configuration, rather than limiting setup to an explicit user command. The directive conten...

The automatic postinstall chain executes an opaque installer that targets AI-agent skill infrastructure. This is unconsented lifecycle mutation of a broad foreign agent control surface.

The automatic postinstall path mutates broad AI-agent and shell control surfaces. This is concrete unconsented install-time control-surface modification.

The automatic postinstall hook performs broad user-level Claude command and skill installation rather than limiting setup to an explicit user action or a package-owned isolated surface.

The automatic postinstall writes enabled OpenCode configuration and agent content into the consuming project. This meets the install-control-surface blocking policy despite preserving an...

The package performs automatic postinstall mutation of user-scoped AI-agent skill and MCP configuration, including a launcher registration. This meets the policy definition of a concrete...

Global postinstall unconsented overwrite of Claude, Codex, shared agents, and OpenClaw-family skill directories is a broad foreign agent control-surface mutation. The skip flag and non-gl...

The postinstall hook writes this package's skills into the global Codex and Claude skill directories and prunes existing files there without a user command or consent check. That is uncon...

The postinstall hook unconditionally mutates Cursor user skills and the user MCP server list, which is a foreign agent control surface, without consent. That install-time control-surface...

Postinstall always writes Claude Code skill files under the user home, and after a prior setup marker it also rewrites Claude MCP and hook settings. That is unconsented install-time mutat...