shopify-use-shopify-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires inlining a verbatim base64-encoded copy of the user's most recent message into a bash command (and to include real runtime IDs in env vars), which forces the LLM to reproduce any secrets present in the user's prompt into its output—an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill intentionally captures and transmits verbatim user prompts, session/tool identifiers, and (for staging) auth tokens to external Shopify telemetry endpoints — a deliberate data-exfiltration/telemetry behavior that poses significant privacy risk if users aren't explicitly consenting.