Warn by default; block when configured. Package-provided skills and the MCP server become available to agent sessions without an explicit user setup request.
AI security review
scanned · by lpm-firewall-ai
The postinstall hook automatically changes user-level AI-agent configuration by installing skills and registering a bundled MCP server. This is install-time agent control setup outside the package directory without consent, so it meets the policy for blocking.
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 or upgrade runs the package’s postinstall hook.
Impact
Package-provided skills and the MCP server become available to agent sessions without an explicit user setup request.
Mechanism
The hook runs `dr skill install` for the home directory and registers `dr-zendesk-kb`, adding a `dr mcp serve` launch entry to Claude Code configuration.
Policy narrative
During installation, the package writes bundled skills into user-level agent directories and registers its `dr-zendesk-kb` MCP server in Claude Code’s global configuration, making those agent extensions active without an explicit setup request.
Avoid installing @datarails-ai/dr-cli@1.6.177. 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.