npm AI-agent policy reports, with evidence.

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...

The package's global postinstall automatically installs PATH-shadowing Claude and Codex shims plus persistent schedulers. Its hard-coded remote sync target and setup-token transfer create...

The automatic lifecycle hook downloads or executes an opaque native payload and uses it to modify Codex and Claude Code integration settings. This is a concrete unconsented AI-agent contr...

The automatic postinstall mutates a foreign AI-agent control surface by globally installing Claude Code, alongside persistent user-environment and application changes. Although no direct...

The automatic global lifecycle chain modifies foreign AI-agent configurations and injects instructions that can cause conversation and attachment transfer. This meets the install-hook abu...

This is concrete install-time mutation of a foreign, broad AI-agent control surface. The automatic lifecycle path establishes persistent hooks and global instructions, so it meets the pub...

The source establishes an unconsented postinstall chain that installs a foreign global AI-agent package. The opt-out and detection guard do not change that the mutation occurs automatical...

This package performs unconsented postinstall execution of an opaque native agent-hook installer and declares modifications to Codex and Claude Code configuration. That meets the install-...

This is an unconsented postinstall mutation of a foreign AI-agent control surface. The automatic global installation is concrete and sufficient for a blocking verdict under the install-co...

This is a concrete automatic postinstall mutation of multiple foreign AI-agent control surfaces, including default installation and activation of a Codex plugin. The absence of confirmed...

The postinstall hook performs automatic, destructive replacement across three foreign AI-agent skill roots. Opt-out support and a narrow subdirectory name do not establish prior user cons...

This package performs automatic postinstall execution that installs hooks into external AI agents and changes a Codex setting. The network-downloaded native payload is not integrity-pinne...

The package uses postinstall output to induce autonomous setup, which writes and hooks foreign global AI-agent configurations. This is an unconsented install-time control-surface mutation...

The automatic postinstall hook writes into multiple foreign global AI-agent directories and installs remotely delivered executable code. That is concrete install-hook abuse under the stat...

The package has a concrete postinstall chain that automatically alters an MCP Chrome integration and invokes a permission-changing command. This meets the install-time foreign agent contr...