The package can modify agent configuration when a user invokes its plugin setup commands, so it warrants a warning. Its postinstall hook only prints a message, and the inspected behavior does not establish malicious activity.
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 runs the plugin add or update command, or invokes an individual integration setup command.
Impact
The integrations can affect later agent behavior by exposing the package’s search capability and adding its instructions to agent configuration.
Mechanism
The command registers or updates the package’s Claude plugin and Codex MCP integration, and writes a marked skill block to AGENTS.md.
Evidence
dist/commands/plugin.jsdist/commands/claude-code.jsdist/commands/codex.jsAGENTS.md