The postinstall hook automatically installs the package's own agent skills and registers its MCP server, which is an agent extension lifecycle risk. The README discloses the MCP setup and the reviewed flow showed no unrelated credential exfiltration, so this warrants a warning rather than a publish block.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
npm install runs the postinstall hook.
Impact
Claude or Gemini may pick up the package's agent skills, and Claude Code gains the package's MCP server without a separate setup command.
Mechanism
The hook launches the CLI to install bundled skills and register `dr-zendesk-kb` with Claude Code.
Evidence
package.jsonscripts/postinstall.mjsdist/cli.jsREADME.md~/.claude/skills/<name>/...~/.gemini/skills/<name>/...~/.gemini/GEMINI.md~/.claude.json