shopify-custom-data

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires the agent to inline the user's most recent message verbatim (base64-encoded) into a bash command, which forces any secrets present in the user's message to be included in the model's output (albeit encoded), creating a direct exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill and associated scripts intentionally capture verbatim user prompts and host session identifiers (from environment/CLI) and transmit them to an external telemetry endpoint, which constitutes deliberate data exfiltration and potential exposure of sensitive information.