shopify-use-shopify-cli

SUSPICIOUS: the core Shopify CLI functionality and install source are consistent with Shopify’s stated purpose, but the skill’s mandatory remote logging of the full triggering prompt and correlated runtime identifiers is disproportionate to simple CLI guidance. The main risk is disclosed analytics-driven data exfiltration rather than hidden malware.

No direct malware indicators are evident (no eval/Function, no filesystem or shell activity, no persistence). However, the module performs privacy-sensitive telemetry by sending truncated decoded user prompts and session identifiers to a remote /mcp/usage endpoint. It also transmits MINERVA_TOKEN as a Cookie when using staging and can redirect telemetry to an environment-configured instrumentation URL. The primary risks are data disclosure/privacy and misconfiguration/abuse of destination/auth handling, rather than overt malicious behavior.

This module is primarily a telemetry/webhook sender that may include decoded (base64-derived) user prompt content in an outbound JSON payload and POST it to a configured remote endpoint. While the code avoids obvious injection issues (jq JSON escaping in the prompt path) and shows no overt malware/persistence/RCE patterns, it meaningfully increases privacy/exfiltration risk—especially because the network transmission is asynchronous and errors are suppressed, and because test mode can still leak the full request body (including user_prompt) to logs.