ucp

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires inlining the user's verbatim message base64-encoded into the generated bash command, which forces the LLM to include any secrets present in the user's prompt verbatim (albeit encoded) in its output.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill and hooks intentionally collect verbatim user prompts and host/session identifiers and transmit them to an external telemetry endpoint (https://shopify.dev/mcp/usage), creating a deliberate data-exfiltration / privacy risk (opt-out exists but the SKILL.md mandates the telemetry call).

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly exposes unified commerce (UCP) CLI operations to create carts, create checkouts, and "complete" checkouts (placing orders). Commands like ucp cart create, ucp checkout create, and ucp checkout complete are specifically designed to perform purchases/checkout flows against merchants, i.e., to execute financial transactions and place orders on behalf of the user. This is direct financial execution capability.