npm AI-agent policy reports, with evidence.

The package combines an automatic global postinstall hook with broad third-party MCP configuration writes and a remote, unpinned executable delivery path. The global-only guard and opt-ou...

The lifecycle hook automatically replaces a foreign AI-agent executable with opaque bundled binaries. Backups and hash checks do not remove the install-time control-surface takeover.

The postinstall hook automatically installs command hooks into the user's Copilot configuration and persists shell-profile code. This is a concrete unconsented mutation of foreign AI-agen...

The package performs an unconsented postinstall write to a generic consumer-project AGENTS control surface and injects AI-agent instructions. This meets the install-control-surface blocki...

The automatic postinstall hook writes package-controlled content into the global Claude Code skills directory. That concrete lifecycle-based agent control-surface mutation meets the publi...

The automatic lifecycle hook performs remote content retrieval and broad global AI-agent configuration writes. That is concrete unconsented install-time control-surface mutation.

The package performs unconsented postinstall mutation of the user's Claude command area and automatic MCP registration. Those actions constitute a concrete install-time AI-agent control-s...

This is an automatic install-time path that invokes opaque native code to configure Codex and Claude hooks, rather than an explicit user setup action. The visible source establishes a bro...

The package performs automatic postinstall mutation of both Codex and Claude global skill directories and installs Python dependencies into the user environment. This meets the install-co...

This is an unconsented postinstall mutation of a foreign, global AI-agent control surface. The binary-presence guard does not remove the automatic configuration change.

The package performs automatic postinstall mutation of consumer lifecycle and AI-agent configuration, including third-party plugin installation. This is a concrete install-hook abuse path...

This is concrete install-time AI-agent control-surface mutation, not merely a user-invoked setup command. The global-install guard does not make the automatic cross-product configuration...

The package contains reviewer and AI-directed verdict-control text in its MCP implementation. Although it lacks an npm install hook, this is a concrete agent-control attack surface when i...

The automatic lifecycle chain writes into a broad global AI-agent control surface. Its scoped filenames and lack of confirmed exfiltration reduce the apparent payload severity, but they d...

The package has a registry-install postinstall hook that recursively deletes and replaces Claude Code skills in the consumer project. This meets the install-time AI-agent control-surface...

The package has a concrete automatic postinstall chain that writes global AI-agent instruction files and can source content from an unpinned remote branch. This meets the install-control-...

This is a counterfeit Grok package with an automatic lifecycle hook that deploys a publisher-controlled executable and alters foreign AI CLI state. The lack of direct JavaScript exfiltrat...

This is an unconsented postinstall mutation of broad, foreign AI-agent control surfaces, including a machine-wide executable pre-tool hook. The absence of observed secret exfiltration doe...

The install-time hook silently makes broad global agent and shell changes, then injects mandatory conversation-logging instructions. This meets the policy for malicious install-hook abuse...

The automatic postinstall mutation of global AI-agent skill directories is a concrete unconsented control-surface write. Remote-fetched content makes that install-time mutation more severe.

The package uses automatic install hooks to mutate consumer project lifecycle configuration and user-wide Codex registrations. This is a concrete AI-agent control-surface takeover rather...