Warn by default; block when configured. Agent sessions may load the installed skills and MCP server after installation; Gemini instructions and Claude configuration are also modified.
AI security review
scanned · by lpm-firewall-ai
The package's postinstall hook automatically installs skills into user-level AI-agent directories and registers an MCP server in Claude configuration. The install-time agent configuration changes meet the stated criteria for AI-agent control hijacking.
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 postinstall hook.
Impact
Agent sessions may load the installed skills and MCP server after installation; Gemini instructions and Claude configuration are also modified.
Mechanism
The hook installs bundled skills into the user's home and registers a Datarails MCP server with Claude Code, without requiring a separate user command.
Policy narrative
On package installation, the postinstall hook runs the skill installer against the user's home directory and registers the `dr-zendesk-kb` MCP server with Claude Code. These automatic writes alter agent skills, instructions, and MCP configuration outside the package directory without an explicit user command.
AI identified this as a dangerous AI-agent capability at 97.0% confidence with low false-positive risk.
Evidence for policy risk
The postinstall hook automatically runs `dr skill install` for the user's home directory.
The same hook automatically registers the `dr-zendesk-kb` MCP server.
The CLI says MCP registration writes `~/.claude.json`; skill installation copies files into Claude and Gemini skill directories and updates Gemini instructions.
Evidence against
The installed skills and MCP server are part of the Datarails CLI's stated functionality.
The hook reports failures and exits successfully; no credential exfiltration was established.
Avoid installing @datarails-ai/dr-cli@1.6.210. 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.