Installation automatically adds a package-owned MCP server to the user's global Claude Code configuration, so residual agent integration risk remains. The inspected source does not establish credential theft or another concrete attack, so this warrants a warning rather than a publish block.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review; source fingerprint signature matched known malicious package; routed for review
Trigger
Installing the package runs its postinstall hook.
Impact
Claude Code gains access to the package's Datarails Help Center tool without a separate registration command. The automatic agent configuration change leaves residual risk, but the inspected source does not establish malicious behavior.
Mechanism
The hook invokes the CLI to install skills and register dr-zendesk-kb; the CLI writes the MCP server command to ~/.claude.json.
Evidence
package.jsonscripts/postinstall.mjsdist/cli.js~/.claude.json