Warn by default; block when configured. Claude Code may load the added skills and MCP server in later sessions without the user explicitly requesting that setup.
AI security review
scanned · by lpm-firewall-ai
The postinstall hook automatically installs assistant skills and registers an MCP server by changing user-level AI-agent configuration. Under the review rules, install-time writes to agent settings outside the package directory without consent are malicious.
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
Any npm installation that runs the package's postinstall hook.
Impact
Claude Code may load the added skills and MCP server in later sessions without the user explicitly requesting that setup.
Mechanism
The hook invokes the CLI to install skills into the user's home directory and register the `dr-zendesk-kb` MCP server with Claude Code.
Policy narrative
On installation, the postinstall hook writes bundled skills into user-level assistant locations and registers a bundled MCP server with Claude Code. These automatic writes alter AI-agent configuration outside the package directory without an explicit user command.
Avoid installing @datarails-ai/dr-cli@1.6.199. 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.