The postinstall hook only prints guidance, while agent configuration changes are exposed through explicit setup commands. The guarded first-party integration capability warrants a warning, but the inspected code does not establish malicious behavior or an automatic install-time attack.
Static reason
One or more suspicious static signals were detected.; source matched previously finalized malicious package; routed for review; previous stored version diff introduced dangerous source
Trigger
A user invokes a plugin add or update command, or the integration-specific install command.
Impact
The agent clients can invoke grepmax capabilities and receive its skill instructions; the inspected source does not show this being triggered by npm installation.
Mechanism
The commands register or refresh the grepmax Claude plugin or Codex MCP server and add package-owned skill instructions to AGENTS.md.
Evidence
dist/commands/claude-code.jsdist/commands/codex.jsdist/commands/plugin.jsscripts/postinstall.jspackage.json