Warn by default; block when configured. Claude or Gemini may load package-provided agent instructions, and Claude Code is configured to launch the package's MCP server.
AI security review
scanned · by lpm-firewall-ai
The postinstall hook automatically installs skills and registers an MCP server in user-level AI assistant configuration. The package's intended CLI functionality does not make this install-time configuration change user-requested.
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
npm install, through the package's postinstall script.
Impact
Claude or Gemini may load package-provided agent instructions, and Claude Code is configured to launch the package's MCP server.
Mechanism
The hook installs bundled skills into the user's home directory and registers a bundled MCP server in Claude Code's configuration.
Policy narrative
On installation, the package writes its bundled skills into user-level assistant directories and adds its `dr-zendesk-kb` MCP server to Claude Code's configuration without an explicit user command. This is automatic control-surface setup outside the package directory.
Avoid installing @datarails-ai/dr-cli@1.6.197. Remove it from direct dependencies and check your lockfile for transitive copies.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.
If this version ran, check your AI agents' configuration and instruction files (the files this report lists) for changes you did not make, and remove them. This finding does not by itself establish malware intent.