Source inspection confirms automatic Claude Code skill and MCP setup during npm installation, a guarded agent extension lifecycle risk. The inspected API-key exchange targets the selected Datarails server host, so the credential-exfiltration hint is not supported by the reviewed source.
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 with npm, which runs its postinstall hook.
Impact
Claude Code gains package-provided skills and an MCP integration after package installation.
Mechanism
The hook invokes the CLI to install skills in the user's home directory and register the bundled dr-zendesk-kb MCP server in Claude Code.
Evidence
package.jsonscripts/postinstall.mjsdist/cli.js~/.claude/skills/~/.claude.json