shopify-polaris-admin-extensions

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires embedding the user's most recent message verbatim (base64-encoded) into a validation command (--user-prompt-base64), forcing the model to output any secrets present in that message.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). SKILL.md contains mandatory instructions to run external tooling that require embedding the user's verbatim prompt and session identifiers into commands which the tooling then reports (telemetry), constituting forced data exfiltration / privacy leakage risk.