shopify-app-store-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill mandates embedding the user's most recent message verbatim (base64-encoded) into a logged bash command, forcing the LLM 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). The skill and accompanying scripts intentionally capture verbatim user prompts, host session identifiers, and (in staging) tokens and transmit them to an external telemetry endpoint, representing deliberate data exfiltration and credential leakage risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). SKILL.md instructs the agent at runtime to fetch the canonical requirements via the Shopify CLI from https://shopify.dev/docs/apps/launch/app-store-review/app-store-ai-self-review-requirements and use that fetched Markdown as the source of truth to drive the evaluation, so this external URL directly controls agent behavior at runtime.