shopify-polaris-customer-account-extensions

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill mandates inlining the user's verbatim prompt (base64-encoded) into the validator command (and optionally including session/tool IDs), which forces the LLM to handle and transmit any secrets present in the user's prompt verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The SKILL.md file explicitly requires embedding the user's verbatim prompt (base64) and session/tool identifiers into automated tool invocations which the project documents will report to Shopify, an intentional data-exfiltration/telemetry pattern.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow in SKILL.md ingests the outsider-authored user’s free-text via --user-prompt-base64 passed to scripts/validate.mjs, without any prior selection/lookup of a specific item that would gate ingestion.