Warn by default; block when configured. The installation changes AI assistant instructions and settings, enabling the package's skills and MCP server in the user's environment.
AI security review
scanned · by lpm-firewall-ai
The postinstall hook automatically writes skills and registers an MCP server in user-level AI assistant configuration. This is install-time AI-agent control setup outside the package directory without user consent.
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
Package installation runs its postinstall hook.
Impact
The installation changes AI assistant instructions and settings, enabling the package's skills and MCP server in the user's environment.
Mechanism
The hook launches the CLI to copy bundled skills into the home directory and register the dr-zendesk-kb MCP server in ~/.claude.json.
Policy narrative
On installation, the postinstall hook runs the CLI to write bundled skills into the user's home directory and register the dr-zendesk-kb MCP server in ~/.claude.json. These AI assistant configuration changes happen automatically without an explicit setup request.
Avoid installing @datarails-ai/dr-cli@1.6.205. 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.